From cf8e9203cc653f0a82639f7ce8089fa92afe6739 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 26 Feb 2026 14:09:42 -0800 Subject: virt: fsl_hypervisor: fix header kernel-doc warnings Correct struct member names to placate kernel-doc warnings: Warning: include/uapi/linux/fsl_hypervisor.h:148 struct member 'local_vaddr' not described in 'fsl_hv_ioctl_memcpy' Warning: include/uapi/linux/fsl_hypervisor.h:148 struct member 'remote_paddr' not described in 'fsl_hv_ioctl_memcpy' Fixes: 6db7199407ca ("drivers/virt: introduce Freescale hypervisor management driver") Signed-off-by: Randy Dunlap Link: https://lore.kernel.org/r/20260226220942.1035295-1-rdunlap@infradead.org Signed-off-by: Christophe Leroy (CS GROUP) --- include/uapi/linux/fsl_hypervisor.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fsl_hypervisor.h b/include/uapi/linux/fsl_hypervisor.h index 1e237fba951f..ab4388441e80 100644 --- a/include/uapi/linux/fsl_hypervisor.h +++ b/include/uapi/linux/fsl_hypervisor.h @@ -114,9 +114,9 @@ struct fsl_hv_ioctl_stop { * @target: the partition ID of the target partition, or -1 for this * partition * @reserved: reserved, must be set to 0 - * @local_addr: user-space virtual address of a buffer in the local + * @local_vaddr: user-space virtual address of a buffer in the local * partition - * @remote_addr: guest physical address of a buffer in the + * @remote_paddr: guest physical address of a buffer in the * remote partition * @count: the number of bytes to copy. Both the local and remote * buffers must be at least 'count' bytes long -- cgit v1.3-14-g43fede From f7a6b9eaff3e6693ba3b19c5812e28538049bbf2 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Fri, 17 Apr 2026 15:30:18 +0100 Subject: bpf: Extend BTF UAPI vlen, kinds to use unused bits BTF maximum vlen is encoded using 16 bits with a maximum vlen of 65535. This has sufficed for structs, function parameters and enumerated type values. However, with upcoming BTF location information - in particular information about inline sites - this limit is surpassed. Use bits 16-23 - currently unused in BTF info - to extend to 24 bits, giving a max vlen of (2^24 - 1), or 16 million. Also extend BTF kind encoding from 5 to 7 bits, giving a maximum available number of kinds of 128. Since with the BTF location work we use another 3 kinds, we are fast approaching the current limit of 32. Convert BTF_MAX_* values to enums to allow them to be encoded in kernel BTF; this will allow us to detect if the running kernel supports a 24-bit vlen or not. Add one for max _possible_ (not used) kind. Fix up a few places in the kernel where a 16-bit vlen is assumed; remove BTF_INFO_MASK as now all bits are used. The vlen expansion was suggested by Andrii in [1]; the kind expansion is tackled here too as it may be needed also to support new kinds in BTF. [1] https://lore.kernel.org/bpf/CAEf4BzZx=X6vGqcA8SPU6D+v6k+TR=ZewebXMuXtpmML058piw@mail.gmail.com/ Suggested-by: Andrii Nakryiko Signed-off-by: Alan Maguire Acked-by: Mykyta Yatsenko Link: https://lore.kernel.org/r/20260417143023.1551481-2-alan.maguire@oracle.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 4 ++-- include/uapi/linux/btf.h | 26 ++++++++++++++------------ kernel/bpf/btf.c | 27 ++++++++++----------------- tools/include/uapi/linux/btf.h | 26 ++++++++++++++------------ 4 files changed, 40 insertions(+), 43 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 48108471c5b1..c82d0d689059 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -415,12 +415,12 @@ static inline bool btf_type_is_array(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; } -static inline u16 btf_type_vlen(const struct btf_type *t) +static inline u32 btf_type_vlen(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); } -static inline u16 btf_vlen(const struct btf_type *t) +static inline u32 btf_vlen(const struct btf_type *t) { return btf_type_vlen(t); } diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 638615ebddc2..618167cab4e6 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -33,20 +33,22 @@ struct btf_header { __u32 layout_len; /* length of layout section */ }; -/* Max # of type identifier */ -#define BTF_MAX_TYPE 0x000fffff -/* Max offset into the string section */ -#define BTF_MAX_NAME_OFFSET 0x00ffffff -/* Max # of struct/union/enum members or func args */ -#define BTF_MAX_VLEN 0xffff +enum btf_max { + /* Max possible kind */ + BTF_MAX_KIND = 0x0000007f, + /* Max # of type identifier */ + BTF_MAX_TYPE = 0x000fffff, + /* Max offset into the string section */ + BTF_MAX_NAME_OFFSET = 0x00ffffff, + /* Max # of struct/union/enum members or func args */ + BTF_MAX_VLEN = 0x00ffffff, +}; struct btf_type { __u32 name_off; /* "info" bits arrangement - * bits 0-15: vlen (e.g. # of struct's members) - * bits 16-23: unused - * bits 24-28: kind (e.g. int, ptr, array...etc) - * bits 29-30: unused + * bits 0-23: vlen (e.g. # of struct's members) + * bits 24-30: kind (e.g. int, ptr, array...etc) * bit 31: kind_flag, currently used by * struct, union, enum, fwd, enum64, * decl_tag and type_tag @@ -65,8 +67,8 @@ struct btf_type { }; }; -#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f) -#define BTF_INFO_VLEN(info) ((info) & 0xffff) +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x7f) +#define BTF_INFO_VLEN(info) ((info) & 0xffffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) enum { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 3c2aaa3c5004..77af44d8a3ad 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -182,7 +182,6 @@ #define BITS_ROUNDUP_BYTES(bits) \ (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) -#define BTF_INFO_MASK 0x9f00ffff #define BTF_INT_MASK 0x0fffffff #define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE) #define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET) @@ -289,7 +288,7 @@ enum verifier_phase { struct resolve_vertex { const struct btf_type *t; u32 type_id; - u16 next_member; + u32 next_member; }; enum visit_state { @@ -2031,7 +2030,7 @@ static int env_stack_push(struct btf_verifier_env *env, } static void env_stack_set_next_member(struct btf_verifier_env *env, - u16 next_member) + u32 next_member) { env->stack[env->top_stack - 1].next_member = next_member; } @@ -3293,7 +3292,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, struct btf *btf = env->btf; u32 struct_size = t->size; u32 offset; - u16 i; + u32 i; meta_needed = btf_type_vlen(t) * sizeof(*member); if (meta_left < meta_needed) { @@ -3369,7 +3368,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env, { const struct btf_member *member; int err; - u16 i; + u32 i; /* Before continue resolving the next_member, * ensure the last member is indeed resolved to a @@ -4447,7 +4446,7 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, const struct btf_enum *enums = btf_type_enum(t); struct btf *btf = env->btf; const char *fmt_str; - u16 i, nr_enums; + u32 i, nr_enums; u32 meta_needed; nr_enums = btf_type_vlen(t); @@ -4555,7 +4554,7 @@ static s32 btf_enum64_check_meta(struct btf_verifier_env *env, const struct btf_enum64 *enums = btf_type_enum64(t); struct btf *btf = env->btf; const char *fmt_str; - u16 i, nr_enums; + u32 i, nr_enums; u32 meta_needed; nr_enums = btf_type_vlen(t); @@ -4683,7 +4682,7 @@ static void btf_func_proto_log(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_param *args = (const struct btf_param *)(t + 1); - u16 nr_args = btf_type_vlen(t), i; + u32 nr_args = btf_type_vlen(t), i; btf_verifier_log(env, "return=%u args=(", t->type); if (!nr_args) { @@ -4929,7 +4928,7 @@ static int btf_datasec_resolve(struct btf_verifier_env *env, { const struct btf_var_secinfo *vsi; struct btf *btf = env->btf; - u16 i; + u32 i; env->resolve_mode = RESOLVE_TBD; for_each_vsi_from(i, v->next_member, v->t, vsi) { @@ -5183,7 +5182,7 @@ static int btf_func_proto_check(struct btf_verifier_env *env, const struct btf_type *ret_type; const struct btf_param *args; const struct btf *btf; - u16 nr_args, i; + u32 nr_args, i; int err; btf = env->btf; @@ -5278,7 +5277,7 @@ static int btf_func_check(struct btf_verifier_env *env, const struct btf_type *proto_type; const struct btf_param *args; const struct btf *btf; - u16 nr_args, i; + u32 nr_args, i; btf = env->btf; proto_type = btf_type_by_id(btf, t->type); @@ -5336,12 +5335,6 @@ static s32 btf_check_meta(struct btf_verifier_env *env, } meta_left -= sizeof(*t); - if (t->info & ~BTF_INFO_MASK) { - btf_verifier_log(env, "[%u] Invalid btf_info:%x", - env->log_type_id, t->info); - return -EINVAL; - } - if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX || BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) { btf_verifier_log(env, "[%u] Invalid kind:%u", diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 638615ebddc2..618167cab4e6 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -33,20 +33,22 @@ struct btf_header { __u32 layout_len; /* length of layout section */ }; -/* Max # of type identifier */ -#define BTF_MAX_TYPE 0x000fffff -/* Max offset into the string section */ -#define BTF_MAX_NAME_OFFSET 0x00ffffff -/* Max # of struct/union/enum members or func args */ -#define BTF_MAX_VLEN 0xffff +enum btf_max { + /* Max possible kind */ + BTF_MAX_KIND = 0x0000007f, + /* Max # of type identifier */ + BTF_MAX_TYPE = 0x000fffff, + /* Max offset into the string section */ + BTF_MAX_NAME_OFFSET = 0x00ffffff, + /* Max # of struct/union/enum members or func args */ + BTF_MAX_VLEN = 0x00ffffff, +}; struct btf_type { __u32 name_off; /* "info" bits arrangement - * bits 0-15: vlen (e.g. # of struct's members) - * bits 16-23: unused - * bits 24-28: kind (e.g. int, ptr, array...etc) - * bits 29-30: unused + * bits 0-23: vlen (e.g. # of struct's members) + * bits 24-30: kind (e.g. int, ptr, array...etc) * bit 31: kind_flag, currently used by * struct, union, enum, fwd, enum64, * decl_tag and type_tag @@ -65,8 +67,8 @@ struct btf_type { }; }; -#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f) -#define BTF_INFO_VLEN(info) ((info) & 0xffff) +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x7f) +#define BTF_INFO_VLEN(info) ((info) & 0xffffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) enum { -- cgit v1.3-14-g43fede From dd59392a3ec23dbe3a3fabadcf3bb847e9592ccd Mon Sep 17 00:00:00 2001 From: Francesco Lavra Date: Tue, 24 Mar 2026 09:47:59 +0100 Subject: iio: ABI: Add quaternion axis modifier This modifier applies to the IIO_ROT channel type, and indicates a data representation that specifies the {x, y, z} components of the normalized quaternion vector. Signed-off-by: Francesco Lavra Reviewed-by: David Lechner Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 15 +++++++++++++++ drivers/iio/industrialio-core.c | 1 + include/uapi/linux/iio/types.h | 1 + tools/iio/iio_event_monitor.c | 1 + 4 files changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 851cfe4f0a05..60dfeff8f2c9 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1755,6 +1755,21 @@ Description: measurement from channel Y. Units after application of scale and offset are milliamps. +What: /sys/bus/iio/devices/iio:deviceX/in_rot_quaternionaxis_raw +KernelVersion: 7.1 +Contact: linux-iio@vger.kernel.org +Description: + Raw value of {x, y, z} components of the quaternion vector. These + components represent the axis about which a rotation occurs, and are + subject to the following constraints: + + - the quaternion vector is normalized, i.e. w^2 + x^2 + y^2 + z^2 = 1 + - the rotation angle is within the [-pi, pi] range, i.e. the w + component (which represents the amount of rotation) is non-negative + + These constraints allow the w value to be calculated from the other + components: w = sqrt(1 - (x^2 + y^2 + z^2)). + What: /sys/.../iio:deviceX/in_energy_en What: /sys/.../iio:deviceX/in_distance_en What: /sys/.../iio:deviceX/in_velocity_sqrt(x^2+y^2+z^2)_en diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 22eefd048ba9..bd6f4f9f4533 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -157,6 +157,7 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_ACTIVE] = "active", [IIO_MOD_REACTIVE] = "reactive", [IIO_MOD_APPARENT] = "apparent", + [IIO_MOD_QUATERNION_AXIS] = "quaternionaxis", }; /* relies on pairs of these shared then separate */ diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 6d269b844271..d7c2bb223651 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -113,6 +113,7 @@ enum iio_modifier { IIO_MOD_ACTIVE, IIO_MOD_REACTIVE, IIO_MOD_APPARENT, + IIO_MOD_QUATERNION_AXIS, }; enum iio_event_type { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 03ca33869ce8..df6c43d7738d 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -145,6 +145,7 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_ACTIVE] = "active", [IIO_MOD_REACTIVE] = "reactive", [IIO_MOD_APPARENT] = "apparent", + [IIO_MOD_QUATERNION_AXIS] = "quaternionaxis", }; static bool event_is_known(struct iio_event_data *event) -- cgit v1.3-14-g43fede From 032d1a3fc0e95ca804213df65ef57f5ced2a867b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 15 Apr 2026 14:42:05 +0200 Subject: wifi: nl80211: document channel opmode change channel width The opmode change notification is entirely unused by existing userspace except for printing out the values. As such, there's no need to keep it perfectly accurate, and the implementation in mac80211 doesn't report it correctly today. Add a note in the documentation that it may not differentiate 80+80 and 160. Reviewed-by: Miriam Rachel Korenblit Link: https://patch.msgid.link/20260415144514.87d5b1ce688f.Ia9a0769d52dcfe56f7b0dff903ed14db3ef04920@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 3d55bf4be36f..072b383d7d3c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1204,10 +1204,12 @@ * user space through the connect result as the user space would have * initiated the connection through the connect request. * - * @NL80211_CMD_STA_OPMODE_CHANGED: An event that notify station's - * ht opmode or vht opmode changes using any of %NL80211_ATTR_SMPS_MODE, - * %NL80211_ATTR_CHANNEL_WIDTH,%NL80211_ATTR_NSS attributes with its - * address(specified in %NL80211_ATTR_MAC). + * @NL80211_CMD_STA_OPMODE_CHANGED: An event that notifies that a station's + * HT opmode or VHT opmode changed using any of %NL80211_ATTR_SMPS_MODE, + * %NL80211_ATTR_CHANNEL_WIDTH, %NL80211_ATTR_NSS attributes with its + * address (specified in %NL80211_ATTR_MAC). + * Note that 80+80 and 160 MHz might not be differentiated, i.e. may + * report %NL80211_CHAN_WIDTH_160 instead of %NL80211_CHAN_WIDTH_80P80. * * @NL80211_CMD_GET_FTM_RESPONDER_STATS: Retrieve FTM responder statistics, in * the %NL80211_ATTR_FTM_RESPONDER_STATS attribute. -- cgit v1.3-14-g43fede From 781c8893a5da8522ae4ded93e5ef3adbe9559300 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Tue, 28 Apr 2026 17:49:06 +0200 Subject: dpll: add pin operational state Add pin-operstate enum and operstate_on_dpll_get callback to report the actual hardware status of a pin with respect to its parent DPLL device. Unlike pin-state (which reflects administrative intent set by the user), operstate reflects what the hardware is actually doing. Defined operational states: - active: pin is qualified and actively used by the DPLL - standby: pin is qualified but not actively used by the DPLL - no-signal: pin does not have a valid signal - qual-failed: pin signal failed qualification The operstate is reported inside the pin-parent-device nested attribute alongside the existing state and phase-offset attributes. Signed-off-by: Ivan Vecera Reviewed-by: Jiri Pirko Reviewed-by: Vadim Fedorenko Reviewed-by: Petr Oros Link: https://patch.msgid.link/20260428154907.2820654-2-ivecera@redhat.com Signed-off-by: Paolo Abeni --- Documentation/driver-api/dpll.rst | 38 +++++++++++++++++++++-------------- Documentation/netlink/specs/dpll.yaml | 31 ++++++++++++++++++++++++++++ drivers/dpll/dpll_netlink.c | 27 +++++++++++++++++++++++++ drivers/dpll/dpll_nl.c | 3 ++- drivers/dpll/dpll_nl.h | 2 +- include/linux/dpll.h | 6 ++++++ include/uapi/linux/dpll.h | 23 +++++++++++++++++++++ 7 files changed, 113 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index 93c191b2d089..37eaef785e30 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -65,35 +65,43 @@ request, where user provides attributes that result in single pin match. Pin selection ============= -In general, selected pin (the one which signal is driving the dpll -device) can be obtained from ``DPLL_A_PIN_STATE`` attribute, and only -one pin shall be in ``DPLL_PIN_STATE_CONNECTED`` state for any dpll -device. +Pin state (``DPLL_A_PIN_STATE``) reflects the administrative intent set +by the user. Pin operational state (``DPLL_A_PIN_OPERSTATE``) reflects +what the hardware is actually doing with the pin. Pin selection can be done either manually or automatically, depending on hardware capabilities and active dpll device work mode (``DPLL_A_MODE`` attribute). The consequence is that there are -differences for each mode in terms of available pin states, as well as -for the states the user can request for a dpll device. +differences for each mode in terms of available pin states the user can +request for a dpll device. -In manual mode (``DPLL_MODE_MANUAL``) the user can request or receive -one of following pin states: +In manual mode (``DPLL_MODE_MANUAL``) the user can request one of +following pin states: -- ``DPLL_PIN_STATE_CONNECTED`` - the pin is used to drive dpll device -- ``DPLL_PIN_STATE_DISCONNECTED`` - the pin is not used to drive dpll +- ``DPLL_PIN_STATE_CONNECTED`` - the pin is selected to drive dpll device +- ``DPLL_PIN_STATE_DISCONNECTED`` - the pin is not selected to drive + dpll device -In automatic mode (``DPLL_MODE_AUTOMATIC``) the user can request or -receive one of following pin states: +In automatic mode (``DPLL_MODE_AUTOMATIC``) the user can request one of +following pin states: - ``DPLL_PIN_STATE_SELECTABLE`` - the pin shall be considered as valid input for automatic selection algorithm - ``DPLL_PIN_STATE_DISCONNECTED`` - the pin shall be not considered as a valid input for automatic selection algorithm -In automatic mode (``DPLL_MODE_AUTOMATIC``) the user can only receive -pin state ``DPLL_PIN_STATE_CONNECTED`` once automatic selection -algorithm locks a dpll device with one of the inputs. +The actual hardware status of a pin is reported via the operational +state (``DPLL_A_PIN_OPERSTATE``) attribute nested under the parent +device: + +- ``DPLL_PIN_OPERSTATE_ACTIVE`` - pin is qualified and actively used + by the DPLL +- ``DPLL_PIN_OPERSTATE_STANDBY`` - pin is qualified but not actively + used by the DPLL +- ``DPLL_PIN_OPERSTATE_NO_SIGNAL`` - pin does not have a valid signal +- ``DPLL_PIN_OPERSTATE_QUAL_FAILED`` - pin signal failed qualification + checks Shared pins =========== diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 40465a3d7fc2..c45de70a47ce 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -212,6 +212,27 @@ definitions: name: selectable doc: pin enabled for automatic input selection render-max: true + - + type: enum + name: pin-operstate + doc: | + defines possible operational states of a pin with respect to its + parent DPLL device, valid values for DPLL_A_PIN_OPERSTATE attribute + entries: + - + name: active + doc: pin is qualified and actively used by the DPLL + value: 1 + - + name: standby + doc: pin is qualified but not actively used by the DPLL + - + name: no-signal + doc: pin does not have a valid signal + - + name: qual-failed + doc: pin signal failed qualification (e.g. frequency or phase monitor) + render-max: true - type: flags name: pin-capabilities @@ -488,6 +509,14 @@ attribute-sets: Value of (DPLL_A_PIN_MEASURED_FREQUENCY % DPLL_PIN_MEASURED_FREQUENCY_DIVIDER) is a fractional part of a measured frequency value. + - + name: operstate + type: u32 + enum: pin-operstate + doc: | + Operational state of the pin with respect to its parent DPLL + device. Unlike state (which reflects the administrative intent), + operstate reflects the actual hardware status. - name: pin-parent-device @@ -501,6 +530,8 @@ attribute-sets: name: prio - name: state + - + name: operstate - name: phase-offset - diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index af7ce62ec55c..05cf946b4be5 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -324,6 +324,30 @@ dpll_msg_add_pin_on_dpll_state(struct sk_buff *msg, struct dpll_pin *pin, return 0; } +static int +dpll_msg_add_pin_operstate(struct sk_buff *msg, struct dpll_pin *pin, + struct dpll_pin_ref *ref, + struct netlink_ext_ack *extack) +{ + const struct dpll_pin_ops *ops = dpll_pin_ops(ref); + struct dpll_device *dpll = ref->dpll; + enum dpll_pin_operstate operstate; + int ret; + + if (!ops->operstate_on_dpll_get) + return 0; + ret = ops->operstate_on_dpll_get(pin, + dpll_pin_on_dpll_priv(dpll, pin), + dpll, dpll_priv(dpll), + &operstate, extack); + if (ret) + return ret; + if (nla_put_u32(msg, DPLL_A_PIN_OPERSTATE, operstate)) + return -EMSGSIZE; + + return 0; +} + static int dpll_msg_add_pin_direction(struct sk_buff *msg, struct dpll_pin *pin, struct dpll_pin_ref *ref, @@ -650,6 +674,9 @@ dpll_msg_add_pin_dplls(struct sk_buff *msg, struct dpll_pin *pin, if (ret) goto nest_cancel; ret = dpll_msg_add_pin_on_dpll_state(msg, pin, ref, extack); + if (ret) + goto nest_cancel; + ret = dpll_msg_add_pin_operstate(msg, pin, ref, extack); if (ret) goto nest_cancel; ret = dpll_msg_add_pin_prio(msg, pin, ref, extack); diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index 1e652340a5d7..58235845fa3d 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -12,11 +12,12 @@ #include /* Common nested types */ -const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_PHASE_OFFSET + 1] = { +const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_OPERSTATE + 1] = { [DPLL_A_PIN_PARENT_ID] = { .type = NLA_U32, }, [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), [DPLL_A_PIN_PRIO] = { .type = NLA_U32, }, [DPLL_A_PIN_STATE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), + [DPLL_A_PIN_OPERSTATE] = NLA_POLICY_RANGE(NLA_U32, 1, 4), [DPLL_A_PIN_PHASE_OFFSET] = { .type = NLA_S64, }, }; diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h index 7419679b6977..fa8280e3dd14 100644 --- a/drivers/dpll/dpll_nl.h +++ b/drivers/dpll/dpll_nl.h @@ -13,7 +13,7 @@ #include /* Common nested types */ -extern const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_PHASE_OFFSET + 1]; +extern const struct nla_policy dpll_pin_parent_device_nl_policy[DPLL_A_PIN_OPERSTATE + 1]; extern const struct nla_policy dpll_pin_parent_pin_nl_policy[DPLL_A_PIN_STATE + 1]; extern const struct nla_policy dpll_reference_sync_nl_policy[DPLL_A_PIN_STATE + 1]; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index b7277a8b484d..b6f16c884b99 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -85,6 +85,12 @@ struct dpll_pin_ops { const struct dpll_device *dpll, void *dpll_priv, enum dpll_pin_state *state, struct netlink_ext_ack *extack); + int (*operstate_on_dpll_get)(const struct dpll_pin *pin, + void *pin_priv, + const struct dpll_device *dpll, + void *dpll_priv, + enum dpll_pin_operstate *operstate, + struct netlink_ext_ack *extack); int (*state_on_pin_set)(const struct dpll_pin *pin, void *pin_priv, const struct dpll_pin *parent_pin, void *parent_pin_priv, diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 871685f7c353..cb363cccf2e2 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -178,6 +178,28 @@ enum dpll_pin_state { DPLL_PIN_STATE_MAX = (__DPLL_PIN_STATE_MAX - 1) }; +/** + * enum dpll_pin_operstate - defines possible operational states of a pin with + * respect to its parent DPLL device, valid values for DPLL_A_PIN_OPERSTATE + * attribute + * @DPLL_PIN_OPERSTATE_ACTIVE: pin is qualified and actively used by the DPLL + * @DPLL_PIN_OPERSTATE_STANDBY: pin is qualified but not actively used by the + * DPLL + * @DPLL_PIN_OPERSTATE_NO_SIGNAL: pin does not have a valid signal + * @DPLL_PIN_OPERSTATE_QUAL_FAILED: pin signal failed qualification (e.g. + * frequency or phase monitor) + */ +enum dpll_pin_operstate { + DPLL_PIN_OPERSTATE_ACTIVE = 1, + DPLL_PIN_OPERSTATE_STANDBY, + DPLL_PIN_OPERSTATE_NO_SIGNAL, + DPLL_PIN_OPERSTATE_QUAL_FAILED, + + /* private: */ + __DPLL_PIN_OPERSTATE_MAX, + DPLL_PIN_OPERSTATE_MAX = (__DPLL_PIN_OPERSTATE_MAX - 1) +}; + /** * enum dpll_pin_capabilities - defines possible capabilities of a pin, valid * flags on DPLL_A_PIN_CAPABILITIES attribute @@ -257,6 +279,7 @@ enum dpll_a_pin { DPLL_A_PIN_PHASE_ADJUST_GRAN, DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET_PPT, DPLL_A_PIN_MEASURED_FREQUENCY, + DPLL_A_PIN_OPERSTATE, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) -- cgit v1.3-14-g43fede From 5d801b59633f6af60bb0e18d3bbb18b7b040a6d9 Mon Sep 17 00:00:00 2001 From: Jackson Lee Date: Tue, 24 Mar 2026 14:03:57 +0900 Subject: media: v4l2-controls: Add control for background detection Add a generic V4L2 boolean control V4L2_CID_MPEG_VIDEO_BACKGROUND_DETECTION that allows encoders to detect background regions in a frame and use fewer bits or skip mode to encode them, potentially reducing bitrate for streams with stationary scenes. Signed-off-by: Jackson Lee Signed-off-by: Nas Chung Reviewed-by: Nicolas Dufresne Signed-off-by: Nicolas Dufresne Signed-off-by: Hans Verkuil --- Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst | 6 ++++++ drivers/media/v4l2-core/v4l2-ctrls-defs.c | 2 ++ include/uapi/linux/v4l2-controls.h | 2 ++ 3 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index c8890cb5e00a..ab865a1a6ba9 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -737,6 +737,12 @@ enum v4l2_mpeg_video_frame_skip_mode - Enable writing sample aspect ratio in the Video Usability Information. Applicable to the H264 encoder. +``V4L2_CID_MPEG_VIDEO_BACKGROUND_DETECTION (boolean)`` + If enabled, the encoder detect a background region in frame and + use low bits or skip mode to encode the background region. + If a lot of scenes are stationary or background, It may help to + reduce the video bitrate. Applicable to the encoder. + .. _v4l2-mpeg-video-h264-vui-sar-idc: ``V4L2_CID_MPEG_VIDEO_H264_VUI_SAR_IDC`` diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index 551426c4cd01..e062f2088490 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -889,6 +889,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_DEC_DISPLAY_DELAY: return "Display Delay"; case V4L2_CID_MPEG_VIDEO_DEC_DISPLAY_DELAY_ENABLE: return "Display Delay Enable"; case V4L2_CID_MPEG_VIDEO_AU_DELIMITER: return "Generate Access Unit Delimiters"; + case V4L2_CID_MPEG_VIDEO_BACKGROUND_DETECTION: return "Background Detection"; case V4L2_CID_MPEG_VIDEO_H263_I_FRAME_QP: return "H263 I-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_H263_P_FRAME_QP: return "H263 P-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_H263_B_FRAME_QP: return "H263 B-Frame QP Value"; @@ -1296,6 +1297,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_MPEG_VIDEO_MPEG4_QPEL: case V4L2_CID_MPEG_VIDEO_REPEAT_SEQ_HEADER: case V4L2_CID_MPEG_VIDEO_AU_DELIMITER: + case V4L2_CID_MPEG_VIDEO_BACKGROUND_DETECTION: case V4L2_CID_WIDE_DYNAMIC_RANGE: case V4L2_CID_IMAGE_STABILIZATION: case V4L2_CID_RDS_RECEPTION: diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 68dd0c4e47b2..affec0ab4781 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -464,6 +464,8 @@ enum v4l2_mpeg_video_intra_refresh_period_type { V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_CYCLIC = 1, }; +#define V4L2_CID_MPEG_VIDEO_BACKGROUND_DETECTION (V4L2_CID_CODEC_BASE + 238) + /* CIDs for the MPEG-2 Part 2 (H.262) codec */ #define V4L2_CID_MPEG_VIDEO_MPEG2_LEVEL (V4L2_CID_CODEC_BASE+270) enum v4l2_mpeg_video_mpeg2_level { -- cgit v1.3-14-g43fede From 829b815e910b8cc7bf36c85005abc3e66b59303b Mon Sep 17 00:00:00 2001 From: Kavita Kavita Date: Mon, 4 May 2026 18:06:23 +0530 Subject: wifi: cfg80211: indicate (Re)Association frame encryption to userspace In SME-in-driver mode, the driver handles the entire (re)association exchange. Userspace (e.g., wpa_supplicant) currently has no explicit indication of whether the (re)association exchange was encrypted, making it difficult to distinguish EPP (Enhanced Privacy Protection, IEEE 802.11bi) associations from non-EPP associations. When (Re)Association frame encryption is used, the (Re)Association Response frame must contain a Key Delivery element as specified in IEEE P802.11bi/D4.0, Table 9-65. Userspace must process this element only when the (Re)Association Response frame is actually encrypted. Processing it unconditionally for unencrypted frames leads to incorrect behavior. Without an explicit indication from the driver, userspace cannot determine whether encryption was used and whether the Key Delivery element is valid. Add a new flag attribute NL80211_ATTR_ASSOC_ENCRYPTED and a corresponding field "assoc_encrypted" in cfg80211_connect_resp_params to indicate that both the (Re)Association Request and Response frames are transmitted encrypted over the air. For mac80211-based drivers, extend cfg80211_rx_assoc_resp_data with the assoc_encrypted field as well, which is then propagated to cfg80211_connect_resp_params. Pass the flag to userspace via NL80211_CMD_CONNECT event. Signed-off-by: Kavita Kavita Link: https://patch.msgid.link/20260504123624.529218-2-kavita.kavita@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 6 ++++++ include/uapi/linux/nl80211.h | 9 +++++++++ net/wireless/mlme.c | 1 + net/wireless/nl80211.c | 4 +++- net/wireless/sme.c | 1 + 5 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 51eded4204cf..b0a908b2ba73 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -8305,6 +8305,7 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr); * as the AC bitmap in the QoS info field * @req_ies: information elements from the (Re)Association Request frame * @req_ies_len: length of req_ies data + * @assoc_encrypted: indicate if the (re)association exchange is encrypted. * @ap_mld_addr: AP MLD address (in case of MLO) * @links: per-link information indexed by link ID, use links[0] for * non-MLO connections @@ -8319,6 +8320,7 @@ struct cfg80211_rx_assoc_resp_data { const u8 *req_ies; size_t req_ies_len; int uapsd_queues; + bool assoc_encrypted; const u8 *ap_mld_addr; struct { u8 addr[ETH_ALEN] __aligned(2); @@ -8838,6 +8840,9 @@ struct cfg80211_fils_resp_params { * @links.status: per-link status code, to report a status code that's not * %WLAN_STATUS_SUCCESS for a given link, it must also be in the * @valid_links bitmap and may have a BSS pointer (which is then released) + * @assoc_encrypted: The driver should set this flag to indicate that the + * (Re)Association Request/Response frames are transmitted encrypted over + * the air. */ struct cfg80211_connect_resp_params { int status; @@ -8847,6 +8852,7 @@ struct cfg80211_connect_resp_params { size_t resp_ie_len; struct cfg80211_fils_resp_params fils; enum nl80211_timeout_reason timeout_reason; + bool assoc_encrypted; const u8 *ap_mld_addr; u16 valid_links; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 072b383d7d3c..e26d65c1b737 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3142,6 +3142,13 @@ enum nl80211_commands { * association response etc., since it's abridged in the beacon. Used * for START_AP etc. * + * @NL80211_ATTR_ASSOC_ENCRYPTED: Flag attribute, used only with the + * %NL80211_CMD_CONNECT event in SME-in-driver mode. The driver should + * set this flag to indicate that both the (Re)Association Request frame + * and the corresponding (Re)Association Response frame are transmitted + * encrypted over the air. Enhanced Privacy Protection (EPP), as defined + * in IEEE P802.11bi/D4.0, mandates this encryption. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3735,6 +3742,8 @@ enum nl80211_attrs { NL80211_ATTR_NAN_MAX_CHAN_SWITCH_TIME, NL80211_ATTR_NAN_PEER_MAPS, + NL80211_ATTR_ASSOC_ENCRYPTED, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index bd72317c4964..d196b5c086cc 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -38,6 +38,7 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, u.assoc_resp.variable), .status = le16_to_cpu(mgmt->u.assoc_resp.status_code), .ap_mld_addr = data->ap_mld_addr, + .assoc_encrypted = data->assoc_encrypted, }; unsigned int link_id; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index cf236307cca9..b96f2f7f67d2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -20660,7 +20660,9 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, (cr->fils.pmk && nla_put(msg, NL80211_ATTR_PMK, cr->fils.pmk_len, cr->fils.pmk)) || (cr->fils.pmkid && - nla_put(msg, NL80211_ATTR_PMKID, WLAN_PMKID_LEN, cr->fils.pmkid))))) + nla_put(msg, NL80211_ATTR_PMKID, WLAN_PMKID_LEN, cr->fils.pmkid)))) || + (cr->assoc_encrypted && + nla_put_flag(msg, NL80211_ATTR_ASSOC_ENCRYPTED))) goto nla_put_failure; if (cr->valid_links) { diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 86e2ccaa678c..b451df3096dd 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1066,6 +1066,7 @@ void cfg80211_connect_done(struct net_device *dev, } ev->cr.status = params->status; ev->cr.timeout_reason = params->timeout_reason; + ev->cr.assoc_encrypted = params->assoc_encrypted; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); -- cgit v1.3-14-g43fede From 4dbd1829045ee4146ae16b0e1ad122d855a694cb Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:45 +0530 Subject: wifi: cfg80211: Add MAC address filter to remain_on_channel Currently the remain_on_channel operation does not support filtering incoming frames by destination MAC address. This prevents use cases such as PASN authentication in the responder side that need to receive frames addressed to a specific MAC during the off-channel period. Add an rx_addr parameter to the remain_on_channel operation callback and propagate it through the call chain from nl80211 to driver implementations. Introduce the extended feature NL80211_EXT_FEATURE_ROC_ADDR_FILTER as a capability gate so that cfg80211 rejects the request if the driver does not advertise support for address filtering. Extract the address from the NL80211_ATTR_MAC attribute when provided in the netlink message and update the tracing infrastructure to include the address in remain_on_channel trace events. The rx_addr parameter is optional and can be NULL, maintaining backward compatibility with existing drivers. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-3-peddolla.reddy@oss.qualcomm.com Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath6kl/cfg80211.c | 3 ++- drivers/net/wireless/ath/wil6210/cfg80211.c | 3 ++- drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c | 4 +++- drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h | 3 ++- drivers/net/wireless/marvell/mwifiex/cfg80211.c | 3 ++- drivers/net/wireless/microchip/wilc1000/cfg80211.c | 3 ++- include/net/cfg80211.h | 2 +- include/uapi/linux/nl80211.h | 11 ++++++++++- net/mac80211/ieee80211_i.h | 3 ++- net/mac80211/offchannel.c | 3 ++- net/wireless/nl80211.c | 11 ++++++++++- net/wireless/rdev-ops.h | 7 ++++--- net/wireless/trace.h | 12 ++++++++---- 13 files changed, 50 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index 739a24a6ad67..cc0f2c45fc3a 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -1,6 +1,7 @@ /* * Copyright (c) 2004-2011 Atheros Communications Inc. * Copyright (c) 2011-2012 Qualcomm Atheros, Inc. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -3033,7 +3034,7 @@ static int ath6kl_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, unsigned int duration, - u64 *cookie) + u64 *cookie, const u8 *rx_addr) { struct ath6kl_vif *vif = ath6kl_vif_from_wdev(wdev); struct ath6kl *ar = ath6kl_priv(vif->ndev); diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index 3d6e5aad48b1..d6ef92cfcbaf 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -2,6 +2,7 @@ /* * Copyright (c) 2012-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -1734,7 +1735,7 @@ static int wil_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, unsigned int duration, - u64 *cookie) + u64 *cookie, const u8 *rx_addr) { struct wil6210_priv *wil = wiphy_to_wil(wiphy); int rc; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index e1752a513c73..92c16a317328 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -970,10 +970,12 @@ exit: * @channel: channel to stay on. * @duration: time in ms to remain on channel. * @cookie: cookie. + * @rx_addr: Address to match against the destination of received frames */ int brcmf_p2p_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *channel, - unsigned int duration, u64 *cookie) + unsigned int duration, u64 *cookie, + const u8 *rx_addr) { struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); struct brcmf_p2p_info *p2p = &cfg->p2p; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h index d3137ebd7158..9f3f01ade2b7 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h @@ -157,7 +157,8 @@ int brcmf_p2p_scan_prep(struct wiphy *wiphy, struct brcmf_cfg80211_vif *vif); int brcmf_p2p_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *channel, - unsigned int duration, u64 *cookie); + unsigned int duration, u64 *cookie, + const u8 *rx_addr); int brcmf_p2p_notify_listen_complete(struct brcmf_if *ifp, const struct brcmf_event_msg *e, void *data); diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index c9a651bdf882..c9daf893472f 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -304,7 +304,8 @@ static int mwifiex_cfg80211_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, - unsigned int duration, u64 *cookie) + unsigned int duration, u64 *cookie, + const u8 *rx_addr) { struct mwifiex_private *priv = mwifiex_netdev_get_priv(wdev->netdev); int ret; diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index 3a774cc44b26..6654fce4ded8 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -1100,7 +1100,8 @@ static void wilc_wfi_remain_on_channel_expired(struct wilc_vif *vif, u64 cookie) static int remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, - unsigned int duration, u64 *cookie) + unsigned int duration, u64 *cookie, + const u8 *rx_addr) { int ret = 0; struct wilc_vif *vif = netdev_priv(wdev->netdev); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b0a908b2ba73..897dbe325b7e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5270,7 +5270,7 @@ struct cfg80211_ops { struct wireless_dev *wdev, struct ieee80211_channel *chan, unsigned int duration, - u64 *cookie); + u64 *cookie, const u8 *rx_addr); int (*cancel_remain_on_channel)(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie); diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e26d65c1b737..8103f2912abc 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -729,7 +729,9 @@ * to remain on the channel. This command is also used as an event to * notify when the requested duration starts (it may take a while for the * driver to schedule this time due to other concurrent needs for the - * radio). + * radio). An optional attribute %NL80211_ATTR_MAC can be used to filter + * incoming frames during remain-on-channel, such that frames + * addressed to the specified destination MAC are reported. * When called, this operation returns a cookie (%NL80211_ATTR_COOKIE) * that will be included with any events pertaining to this request; * the cookie is also used to cancel the request. @@ -7040,6 +7042,12 @@ enum nl80211_feature_flags { * (NL80211_CMD_AUTHENTICATE) in non-AP STA mode, as specified in * "IEEE P802.11bi/D4.0, 12.16.5". * + * @NL80211_EXT_FEATURE_ROC_ADDR_FILTER: Driver supports MAC address + * filtering during remain-on-channel. When %NL80211_ATTR_MAC is + * provided with %NL80211_CMD_REMAIN_ON_CHANNEL, the driver will + * forward frames with a matching MAC address to userspace during + * the off-channel period. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -7119,6 +7127,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_EPPKE, NL80211_EXT_FEATURE_ASSOC_FRAME_ENCRYPTION, NL80211_EXT_FEATURE_IEEE8021X_AUTH, + NL80211_EXT_FEATURE_ROC_ADDR_FILTER, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index e23e347f870d..76ed7aa7d8cd 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2097,7 +2097,8 @@ void ieee80211_roc_purge(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); int ieee80211_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, - unsigned int duration, u64 *cookie); + unsigned int duration, u64 *cookie, + const u8 *rx_addr); int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie); int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 10c962d28037..83e4be06039e 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -706,7 +706,8 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, int ieee80211_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, - unsigned int duration, u64 *cookie) + unsigned int duration, u64 *cookie, + const u8 *rx_addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_local *local = sdata->local; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b96f2f7f67d2..c5879056e694 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14133,6 +14133,7 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, unsigned int link_id = nl80211_link_id(info->attrs); struct wireless_dev *wdev = info->user_ptr[1]; struct cfg80211_chan_def chandef; + const u8 *rx_addr = NULL; struct sk_buff *msg; void *hdr; u64 cookie; @@ -14145,6 +14146,14 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, duration = nla_get_u32(info->attrs[NL80211_ATTR_DURATION]); + if (info->attrs[NL80211_ATTR_MAC]) + rx_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); + + if (rx_addr && + !wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_ROC_ADDR_FILTER)) + return -EOPNOTSUPP; + if (!rdev->ops->remain_on_channel || !(rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)) return -EOPNOTSUPP; @@ -14192,7 +14201,7 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, } err = rdev_remain_on_channel(rdev, wdev, chandef.chan, - duration, &cookie); + duration, &cookie, rx_addr); if (err) goto free_msg; diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index bba239a068f6..d97d5c08d135 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -736,12 +736,13 @@ static inline int rdev_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct ieee80211_channel *chan, - unsigned int duration, u64 *cookie) + unsigned int duration, u64 *cookie, const u8 *rx_addr) { int ret; - trace_rdev_remain_on_channel(&rdev->wiphy, wdev, chan, duration); + trace_rdev_remain_on_channel(&rdev->wiphy, wdev, chan, duration, + rx_addr); ret = rdev->ops->remain_on_channel(&rdev->wiphy, wdev, chan, - duration, cookie); + duration, cookie, rx_addr); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index eb5bedf9c92a..938fea1fe9d8 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2155,22 +2155,26 @@ DEFINE_EVENT(rdev_pmksa, rdev_del_pmksa, TRACE_EVENT(rdev_remain_on_channel, TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, - unsigned int duration), - TP_ARGS(wiphy, wdev, chan, duration), + unsigned int duration, const u8 *rx_addr), + TP_ARGS(wiphy, wdev, chan, duration, rx_addr), TP_STRUCT__entry( WIPHY_ENTRY WDEV_ENTRY CHAN_ENTRY __field(unsigned int, duration) + MAC_ENTRY(rx_addr) ), TP_fast_assign( WIPHY_ASSIGN; WDEV_ASSIGN; CHAN_ASSIGN(chan); __entry->duration = duration; + MAC_ASSIGN(rx_addr, rx_addr); ), - TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", " CHAN_PR_FMT ", duration: %u", - WIPHY_PR_ARG, WDEV_PR_ARG, CHAN_PR_ARG, __entry->duration) + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", " CHAN_PR_FMT + ", duration: %u, %pM", + WIPHY_PR_ARG, WDEV_PR_ARG, CHAN_PR_ARG, __entry->duration, + __entry->rx_addr) ); TRACE_EVENT(rdev_return_int_cookie, -- cgit v1.3-14-g43fede From 55f23d68f93a4cce394885886cdcd4015c35e951 Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:46 +0530 Subject: wifi: cfg80211/mac80211: Add NL80211_IFTYPE_PD for PD PASN and PMSR operations Add a new wdev-only interface type NL80211_IFTYPE_PD to support Proximity Detection (PD) operations such as PASN and peer measurement operations. This interface type operates without a netdev, similar to P2P_DEVICE and NAN interfaces. Implement support across cfg80211 and mac80211 layers with PD-specific checks gated by the NL80211_EXT_FEATURE_SECURE_RTT feature flag, management frame registration and transmission capabilities, and proper channel context handling where PD interfaces are excluded from bandwidth calculations. Update mac80211 to recognize the new interface type in the relevant paths for this management-only interface. PD discovery can be performed on any available interface, such as NL80211_IFTYPE_STATION. If PD/PMSR uses the MAC address of an existing interface type, such as NL80211_IFTYPE_STATION, then pairing and measurement shall use that same interface. If PD/PMSR uses a different MAC address, such as a random MAC address, then pairing and measurement can be performed on a new NL80211_IFTYPE_PD interface created with that random MAC address. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-4-peddolla.reddy@oss.qualcomm.com [fix comment style] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ net/mac80211/cfg.c | 2 ++ net/mac80211/chan.c | 2 ++ net/mac80211/iface.c | 6 +++++- net/mac80211/offchannel.c | 1 + net/mac80211/rx.c | 7 +++++++ net/mac80211/util.c | 1 + net/wireless/chan.c | 2 ++ net/wireless/core.c | 1 + net/wireless/mlme.c | 1 + net/wireless/nl80211.c | 27 +++++++++++++++++++++++++-- net/wireless/reg.c | 3 +++ net/wireless/util.c | 4 +++- 13 files changed, 55 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8103f2912abc..69e13cd7978a 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3842,6 +3842,7 @@ enum nl80211_attrs { * @NL80211_IFTYPE_NAN_DATA: NAN data interface type (netdev); NAN data * interfaces can only be brought up (IFF_UP) when a NAN interface * already exists and NAN has been started (using %NL80211_CMD_START_NAN). + * @NL80211_IFTYPE_PD: PD device interface type (not a netdev) * @NL80211_IFTYPE_MAX: highest interface type number currently defined * @NUM_NL80211_IFTYPES: number of defined interface types * @@ -3864,6 +3865,7 @@ enum nl80211_iftype { NL80211_IFTYPE_OCB, NL80211_IFTYPE_NAN, NL80211_IFTYPE_NAN_DATA, + NL80211_IFTYPE_PD, /* keep last */ NUM_NL80211_IFTYPES, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c71af8878562..413dd73e8815 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -716,6 +716,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct wireless_dev *wdev, case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_PD: case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: case NL80211_IFTYPE_P2P_CLIENT: @@ -3459,6 +3460,7 @@ static int ieee80211_scan(struct wiphy *wiphy, } break; case NL80211_IFTYPE_NAN: + case NL80211_IFTYPE_PD: default: return -EOPNOTSUPP; } diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 9683d3e6e1d2..16ee79566e50 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -535,6 +535,7 @@ ieee80211_get_width_of_link(struct ieee80211_link_data *link) case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_NAN_DATA: + case NL80211_IFTYPE_PD: WARN_ON_ONCE(1); break; } @@ -1532,6 +1533,7 @@ ieee80211_link_chanctx_reservation_complete(struct ieee80211_link_data *link) case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_NAN_DATA: + case NL80211_IFTYPE_PD: case NUM_NL80211_IFTYPES: WARN_ON(1); break; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 683d8db4da14..84e8e78d1573 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1400,6 +1400,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_NAN: + case NL80211_IFTYPE_PD: /* no special treatment */ break; case NL80211_IFTYPE_NAN_DATA: @@ -1532,7 +1533,8 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) FIF_PROBE_REQ); if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && - sdata->vif.type != NL80211_IFTYPE_NAN) + sdata->vif.type != NL80211_IFTYPE_NAN && + sdata->vif.type != NL80211_IFTYPE_PD) changed |= ieee80211_reset_erp_info(sdata); ieee80211_link_info_change_notify(sdata, &sdata->deflink, changed); @@ -1548,6 +1550,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) break; case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: + case NL80211_IFTYPE_PD: break; default: /* not reached */ @@ -1988,6 +1991,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.bssid = sdata->vif.addr; break; case NL80211_IFTYPE_NAN_DATA: + case NL80211_IFTYPE_PD: break; case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_WDS: diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 83e4be06039e..8bec39b099a0 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -895,6 +895,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, } break; case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_PD: need_offchan = true; break; case NL80211_IFTYPE_NAN: diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index e1f376e0620c..4c788328c820 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4672,6 +4672,13 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) /* Unicast secure management frames */ return ether_addr_equal(sdata->vif.addr, hdr->addr1) && ieee80211_is_unicast_robust_mgmt_frame(skb); + case NL80211_IFTYPE_PD: + /* + * Accept only authentication frames (PASN) addressed to + * this interface. + */ + return ieee80211_is_auth(hdr->frame_control) && + ether_addr_equal(sdata->vif.addr, hdr->addr1); default: break; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 89e82d34ae48..61ec2116fab2 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2210,6 +2210,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_PD: /* nothing to do */ break; case NL80211_IFTYPE_UNSPECIFIED: diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 8b94c0de80ad..8954ac1659c1 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -817,6 +817,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN_DATA: + case NL80211_IFTYPE_PD: break; case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_UNSPECIFIED: @@ -941,6 +942,7 @@ bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev) /* Can NAN type be considered as beaconing interface? */ case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_NAN_DATA: + case NL80211_IFTYPE_PD: break; case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_WDS: diff --git a/net/wireless/core.c b/net/wireless/core.c index 345a83fe428f..9a6f8ffe7ba9 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1519,6 +1519,7 @@ void cfg80211_leave_locked(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_NAN_DATA: + case NL80211_IFTYPE_PD: /* nothing to do */ break; case NL80211_IFTYPE_UNSPECIFIED: diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index d196b5c086cc..50ee462e5eac 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -945,6 +945,7 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, * fall through, P2P device only supports * public action frames */ + case NL80211_IFTYPE_PD: default: err = -EOPNOTSUPP; break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c5879056e694..85096c8964ff 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1842,6 +1842,11 @@ static int nl80211_key_allowed(struct wireless_dev *wdev) NL80211_EXT_FEATURE_SECURE_NAN)) return 0; return -EINVAL; + case NL80211_IFTYPE_PD: + if (wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_SECURE_RTT)) + return 0; + return -EINVAL; case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_MONITOR: @@ -4938,6 +4943,7 @@ static int _nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; if ((type == NL80211_IFTYPE_P2P_DEVICE || type == NL80211_IFTYPE_NAN || + type == NL80211_IFTYPE_PD || rdev->wiphy.features & NL80211_FEATURE_MAC_ON_CREATE) && info->attrs[NL80211_ATTR_MAC]) { nla_memcpy(params.macaddr, info->attrs[NL80211_ATTR_MAC], @@ -4994,8 +5000,9 @@ static int _nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) break; case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_PD: /* - * P2P Device and NAN do not have a netdev, so don't go + * P2P Device, NAN and PD do not have a netdev, so don't go * through the netdev notifier and must be added here */ cfg80211_init_wdev(wdev); @@ -10869,7 +10876,8 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) wiphy = &rdev->wiphy; - if (wdev->iftype == NL80211_IFTYPE_NAN) + if (wdev->iftype == NL80211_IFTYPE_NAN || + wdev->iftype == NL80211_IFTYPE_PD) return -EOPNOTSUPP; if (!rdev->ops->scan) @@ -14290,6 +14298,11 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) WIPHY_NAN_FLAGS_USERSPACE_DE)) return -EOPNOTSUPP; break; + case NL80211_IFTYPE_PD: + if (!wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_SECURE_RTT)) + return -EOPNOTSUPP; + break; default: return -EOPNOTSUPP; } @@ -14354,6 +14367,11 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) WIPHY_NAN_FLAGS_USERSPACE_DE)) return -EOPNOTSUPP; break; + case NL80211_IFTYPE_PD: + if (!wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_SECURE_RTT)) + return -EOPNOTSUPP; + break; default: return -EOPNOTSUPP; } @@ -14479,6 +14497,11 @@ static int nl80211_tx_mgmt_cancel_wait(struct sk_buff *skb, struct genl_info *in NL80211_EXT_FEATURE_SECURE_NAN)) return -EOPNOTSUPP; break; + case NL80211_IFTYPE_PD: + if (!wiphy_ext_feature_isset(wdev->wiphy, + NL80211_EXT_FEATURE_SECURE_RTT)) + return -EOPNOTSUPP; + break; default: return -EOPNOTSUPP; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 5db2121c0b57..1e8214d6b6d8 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2412,6 +2412,9 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) case NL80211_IFTYPE_NAN_DATA: /* NAN channels are checked in NL80211_IFTYPE_NAN interface */ break; + case NL80211_IFTYPE_PD: + /* we have no info, but PD is also pretty universal */ + continue; default: /* others not implemented for now */ WARN_ON_ONCE(1); diff --git a/net/wireless/util.c b/net/wireless/util.c index 95ae06e94f10..b638e205c71e 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1211,7 +1211,8 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, /* cannot change into P2P device or NAN */ if (ntype == NL80211_IFTYPE_P2P_DEVICE || - ntype == NL80211_IFTYPE_NAN) + ntype == NL80211_IFTYPE_NAN || + ntype == NL80211_IFTYPE_PD) return -EOPNOTSUPP; if (!rdev->ops->change_virtual_intf || @@ -1276,6 +1277,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_NAN: + case NL80211_IFTYPE_PD: WARN_ON(1); break; } -- cgit v1.3-14-g43fede From b47a6e4d662976efbe53518cb22cf7df86d19c75 Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:47 +0530 Subject: wifi: cfg80211: add start/stop proximity detection commands Currently, the proximity detection (PD) interface type has no start/stop commands defined, preventing user space from controlling PD operations through the nl80211 interface. Add NL80211_CMD_START_PD and NL80211_CMD_STOP_PD commands to allow user space to start and stop a PD interface. Add the corresponding start_pd and stop_pd operations to cfg80211_ops and ieee80211_ops, along with nl80211 command handlers, rdev wrappers, and tracing support. Validate that drivers advertising PD interface support implement the required operations. Handle PD interface teardown during device unregistration and when the interface leaves the network. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-5-peddolla.reddy@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 5 ++++ include/uapi/linux/nl80211.h | 9 ++++++++ net/wireless/core.c | 35 +++++++++++++++++++++++++++- net/wireless/core.h | 2 ++ net/wireless/nl80211.c | 54 ++++++++++++++++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 19 ++++++++++++++++ net/wireless/trace.h | 10 ++++++++ 7 files changed, 133 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 897dbe325b7e..8f010af419bf 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5088,6 +5088,9 @@ struct mgmt_frame_regs { * links by calling cfg80211_mlo_reconf_add_done(). When calling * cfg80211_mlo_reconf_add_done() the bss pointer must be given for each * link for which MLO reconfiguration 'add' operation was requested. + * + * @start_pd: Start the PD interface. + * @stop_pd: Stop the PD interface. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -5464,6 +5467,8 @@ struct cfg80211_ops { struct cfg80211_ml_reconf_req *req); int (*set_epcs)(struct wiphy *wiphy, struct net_device *dev, bool val); + int (*start_pd)(struct wiphy *wiphy, struct wireless_dev *wdev); + void (*stop_pd)(struct wiphy *wiphy, struct wireless_dev *wdev); }; /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 69e13cd7978a..704607824b8a 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1419,6 +1419,12 @@ * identifying the evacuated channel. * User space may reconfigure the local schedule in response to this * notification. + * @NL80211_CMD_START_PD: Start PD operation, identified by its + * %NL80211_ATTR_WDEV interface. This interface must have been previously + * created with %NL80211_CMD_NEW_INTERFACE. + * @NL80211_CMD_STOP_PD: Stop the PD operation, identified by + * its %NL80211_ATTR_WDEV interface. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1694,6 +1700,9 @@ enum nl80211_commands { NL80211_CMD_NAN_CHANNEL_EVAC, + NL80211_CMD_START_PD, + NL80211_CMD_STOP_PD, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/net/wireless/core.c b/net/wireless/core.c index 9a6f8ffe7ba9..4dd1981a3629 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -322,6 +322,28 @@ int cfg80211_nan_set_local_schedule(struct cfg80211_registered_device *rdev, return 0; } +void cfg80211_stop_pd(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + lockdep_assert_held(&rdev->wiphy.mtx); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_PD)) + return; + + if (!rdev->ops->stop_pd) + return; + + if (!wdev_running(wdev)) + return; + + cfg80211_pmsr_wdev_down(wdev); + + rdev_stop_pd(rdev, wdev); + wdev->is_running = false; + + rdev->opencount--; +} + void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); @@ -351,6 +373,9 @@ void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) case NL80211_IFTYPE_NAN: cfg80211_stop_nan(rdev, wdev); break; + case NL80211_IFTYPE_PD: + cfg80211_stop_pd(rdev, wdev); + break; default: break; } @@ -846,6 +871,9 @@ int wiphy_register(struct wiphy *wiphy) (!rdev->ops->tdls_channel_switch || !rdev->ops->tdls_cancel_channel_switch))) return -EINVAL; + if (WARN_ON((wiphy->interface_modes & BIT(NL80211_IFTYPE_PD)) && + (!rdev->ops->start_pd || !rdev->ops->stop_pd))) + return -EINVAL; if (WARN_ON((wiphy->interface_modes & BIT(NL80211_IFTYPE_NAN)) && (!rdev->ops->start_nan || !rdev->ops->stop_nan || @@ -1408,6 +1436,9 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, case NL80211_IFTYPE_NAN: cfg80211_stop_nan(rdev, wdev); break; + case NL80211_IFTYPE_PD: + cfg80211_stop_pd(rdev, wdev); + break; default: break; } @@ -1516,10 +1547,12 @@ void cfg80211_leave_locked(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_NAN: cfg80211_stop_nan(rdev, wdev); break; + case NL80211_IFTYPE_PD: + cfg80211_stop_pd(rdev, wdev); + break; case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_NAN_DATA: - case NL80211_IFTYPE_PD: /* nothing to do */ break; case NL80211_IFTYPE_UNSPECIFIED: diff --git a/net/wireless/core.h b/net/wireless/core.h index 0e6f9bd4ba1b..df47ed6208a5 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -557,6 +557,8 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, void cfg80211_stop_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); +void cfg80211_stop_pd(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev); int cfg80211_nan_set_local_schedule(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 85096c8964ff..8e20fb714eff 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -16638,6 +16638,46 @@ static int nl80211_nan_change_config(struct sk_buff *skb, return rdev_nan_change_conf(rdev, wdev, &conf, changed); } +static int nl80211_start_pd(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = info->user_ptr[1]; + int err; + + if (wdev->iftype != NL80211_IFTYPE_PD) + return -EOPNOTSUPP; + + if (wdev_running(wdev)) + return -EEXIST; + + if (rfkill_blocked(rdev->wiphy.rfkill)) + return -ERFKILL; + + if (!rdev->ops->start_pd) + return -EOPNOTSUPP; + + err = rdev_start_pd(rdev, wdev); + if (err) + return err; + wdev->is_running = true; + rdev->opencount++; + + return 0; +} + +static int nl80211_stop_pd(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = info->user_ptr[1]; + + if (wdev->iftype != NL80211_IFTYPE_PD) + return -EOPNOTSUPP; + + cfg80211_stop_pd(rdev, wdev); + + return 0; +} + void cfg80211_nan_match(struct wireless_dev *wdev, struct cfg80211_nan_match_params *match, gfp_t gfp) { @@ -19805,6 +19845,20 @@ static const struct genl_small_ops nl80211_small_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_WDEV_UP), }, + { + .cmd = NL80211_CMD_START_PD, + .doit = nl80211_start_pd, + .flags = GENL_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_WDEV | + NL80211_FLAG_NEED_RTNL), + }, + { + .cmd = NL80211_CMD_STOP_PD, + .doit = nl80211_stop_pd, + .flags = GENL_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_WDEV_UP | + NL80211_FLAG_NEED_RTNL), + }, { .cmd = NL80211_CMD_SET_MCAST_RATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index d97d5c08d135..63c26e8b1139 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1093,6 +1093,25 @@ rdev_nan_set_peer_sched(struct cfg80211_registered_device *rdev, return ret; } +static inline int rdev_start_pd(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + int ret; + + trace_rdev_start_pd(&rdev->wiphy, wdev); + ret = rdev->ops->start_pd(&rdev->wiphy, wdev); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void rdev_stop_pd(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + trace_rdev_stop_pd(&rdev->wiphy, wdev); + rdev->ops->stop_pd(&rdev->wiphy, wdev); + trace_rdev_return_void(&rdev->wiphy); +} + static inline int rdev_set_mac_acl(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_acl_data *params) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 938fea1fe9d8..a68d356fe127 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2375,6 +2375,16 @@ DEFINE_EVENT(wiphy_wdev_evt, rdev_stop_nan, TP_ARGS(wiphy, wdev) ); +DEFINE_EVENT(wiphy_wdev_evt, rdev_start_pd, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + +DEFINE_EVENT(wiphy_wdev_evt, rdev_stop_pd, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + TRACE_EVENT(rdev_add_nan_func, TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, const struct cfg80211_nan_func *func), -- cgit v1.3-14-g43fede From 18709c618d3b4b2990f202a436784f4c36e2c193 Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:48 +0530 Subject: wifi: cfg80211: add proximity detection capabilities to PMSR Introduce Proximity Detection (PD) capabilities in Peer Measurement Service (PMSR) as defined in the Wi-Fi Alliance specification "Proximity Ranging (PR) Implementation Consideration Draft 1.9 Rev 1 section 3.3". This enables devices to advertise peer to peer ranging support. Restructure FTM capabilities in cfg80211_pmsr_capabilities to replace the single support_rsta flag with nested ista and rsta sub-structs, each carrying per-mode flags for Non-Trigger Based (NTB), Trigger Based (TB), and EDCA based ranging. This allows drivers to advertise detailed role and protocol support for both initiator and responder roles. Add support to pass additional ISTA and RSTA role capabilities to userspace using new nested ISTA_CAPS and RSTA_CAPS attributes. The legacy RSTA_SUPPORT flag is retained for backward compatibility. Add NL80211_PMSR_FTM_CAPA_ATTR_TYPE_CAPS nested attribute using the nl80211_peer_measurement_ftm_type_capa enum with two sub-flags: NL80211_PMSR_FTM_TYPE_CAPA_ATTR_INFRA_SUPPORT for STA-to-AP or AP-to-STA ranging, and NL80211_PMSR_FTM_TYPE_CAPA_ATTR_PD_SUPPORT for peer-to-peer ranging. Add CONCURRENT_ISTA_RSTA_SUPPORT as a FTM capability flag indicating the device can simultaneously act as initiator and responder in a multi-peer measurement request. Extend FTM capabilities with antenna configuration fields (max_no_of_tx_antennas, max_no_of_rx_antennas) for the PR Element during PASN negotiation, and ranging interval limits (min_allowed_ranging_interval_edca, min_allowed_ranging_interval_ntb) to advertise device timing constraints for EDCA and NTB-based ranging. Update the FTM request validation path in pmsr.c to check RSTA requests against the per-mode rsta capabilities (NTB, TB, EDCA), rejecting requests for modes the device does not support. Co-developed-by: Kavita Kavita Signed-off-by: Kavita Kavita Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-6-peddolla.reddy@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 60 ++++++++++++++++++++++++++++- include/uapi/linux/nl80211.h | 78 +++++++++++++++++++++++++++++++++++++ net/wireless/nl80211.c | 91 +++++++++++++++++++++++++++++++++++++++++++- net/wireless/pmsr.c | 22 ++++++++++- 4 files changed, 245 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8f010af419bf..98943a510112 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5911,7 +5911,45 @@ cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); * (0 means unknown) * @ftm.max_total_ltf_rx: maximum total number of LTFs that can be received * (0 means unknown) - * @ftm.support_rsta: supports operating as RSTA in PMSR FTM request + * @ftm.ista: initiator role capabilities + * @ftm.ista.support_ntb: supports operating as ISTA in PMSR FTM request for + * NTB ranging. + * @ftm.ista.support_tb: supports operating as ISTA in PMSR FTM request for + * TB ranging. + * @ftm.ista.support_edca: supports operating as ISTA in PMSR FTM request for + * EDCA based ranging. + * @ftm.rsta: responder role capabilities + * @ftm.rsta.support_ntb: supports operating as RSTA in PMSR FTM request for + * NTB ranging. + * @ftm.rsta.support_tb: supports operating as RSTA in PMSR FTM request for + * TB ranging. + * @ftm.rsta.support_edca: supports operating as RSTA in PMSR FTM request for + * EDCA based ranging. + * @ftm.max_no_of_tx_antennas: maximum number of transmit antennas supported for + * EDCA based ranging (0 means unknown) + * @ftm.max_no_of_rx_antennas: maximum number of receive antennas supported for + * EDCA based ranging (0 means unknown) + * @ftm.min_allowed_ranging_interval_edca: Minimum EDCA ranging + * interval supported by the device in milli seconds. (0 means unknown). + * Applications can use this value to estimate the burst period to be + * given in the FTM request for the EDCA based ranging case. If + * non-zero, this value will be used to validate the burst period in + * the FTM request. + * @ftm.min_allowed_ranging_interval_ntb: Minimum NTB ranging + * interval supported by the device in milli seconds. (0 means unknown). + * Applications can use this value to estimate the burst period to be + * given in the FTM request for the NTB ranging case. If non-zero, + * this value will be used to validate the nominal time in the FTM + * request. + * @ftm.type: ranging type capabilities + * @ftm.type.infra_support: supports infrastructure ranging (STA-to-AP or + * AP-to-STA) as part of Proximity Detection + * @ftm.type.pd_support: supports peer-to-peer ranging as mentioned in the + * specification "PR Implementation Consideration Draft 1.9 rev 1" where + * PD stands for proximity detection + * @ftm.concurrent_ista_rsta_support: indicates if the device can + * simultaneously act as initiator and responder in a multi-peer + * measurement request. Only valid if @ftm.rsta_support is set. */ struct cfg80211_pmsr_capabilities { unsigned int max_peers; @@ -5937,7 +5975,25 @@ struct cfg80211_pmsr_capabilities { u8 max_rx_sts; u8 max_total_ltf_tx; u8 max_total_ltf_rx; - u8 support_rsta:1; + struct { + u8 support_ntb:1, + support_tb:1, + support_edca:1; + } ista; + struct { + u8 support_ntb:1, + support_tb:1, + support_edca:1; + } rsta; + u8 max_no_of_tx_antennas; + u8 max_no_of_rx_antennas; + u32 min_allowed_ranging_interval_edca; + u32 min_allowed_ranging_interval_ntb; + struct { + u8 infra_support:1, + pd_support:1; + } type; + u8 concurrent_ista_rsta_support:1; } ftm; }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 704607824b8a..ea0acce724ca 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -8111,6 +8111,46 @@ enum nl80211_peer_measurement_attrs { * This limits the allowed combinations of LTF repetitions and STS. * @NL80211_PMSR_FTM_CAPA_ATTR_RSTA_SUPPORT: flag attribute indicating the * device supports operating as the RSTA in PMSR FTM request + * @NL80211_PMSR_FTM_CAPA_ATTR_ISTA_CAPS: nested attribute containing ISTA + * (initiator) role capabilities. Uses the same sub-attributes as + * %NL80211_PMSR_FTM_CAPA_ATTR_RSTA_CAPS. + * @NL80211_PMSR_FTM_CAPA_ATTR_RSTA_CAPS: nested attribute containing RSTA + * (responder) role capabilities. + * @NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_NTB: flag attribute (used inside + * %NL80211_PMSR_FTM_CAPA_ATTR_ISTA_CAPS or + * %NL80211_PMSR_FTM_CAPA_ATTR_RSTA_CAPS) indicating NTB ranging support. + * @NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_TB: flag attribute (used inside + * %NL80211_PMSR_FTM_CAPA_ATTR_ISTA_CAPS or + * %NL80211_PMSR_FTM_CAPA_ATTR_RSTA_CAPS) indicating TB ranging support. + * @NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_EDCA: flag attribute (used inside + * %NL80211_PMSR_FTM_CAPA_ATTR_ISTA_CAPS or + * %NL80211_PMSR_FTM_CAPA_ATTR_RSTA_CAPS) indicating EDCA based ranging + * support. + * @NL80211_PMSR_FTM_CAPA_ATTR_TYPE_CAPS: nested attribute containing ranging + * type capabilities. Uses sub-attributes from + * &enum nl80211_peer_measurement_ftm_type_capa. + * @NL80211_PMSR_FTM_CAPA_ATTR_CONCURRENT_ISTA_RSTA_SUPPORT: flag attribute + * indicating that the device can simultaneously act as initiator and + * responder in a multi-peer measurement request. Only valid if + * @NL80211_PMSR_FTM_CAPA_ATTR_RSTA_SUPPORT is set. + * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_NUM_TX_ANTENNAS: u32 attribute indicating + * the maximum number of transmit antennas supported for EDCA based ranging + * (0 means unknown) + * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_NUM_RX_ANTENNAS: u32 attribute indicating + * the maximum number of receive antennas supported for EDCA based ranging + * (0 means unknown) + * @NL80211_PMSR_FTM_CAPA_ATTR_MIN_INTERVAL_EDCA: u32 attribute indicating + * the minimum EDCA ranging interval supported by the device + * in milli seconds. (0 means unknown). Applications can use this value + * to estimate the burst period to be given in the FTM request for the + * EDCA based ranging case. If non-zero, this value will be used to + * validate the burst period in the FTM request. + * @NL80211_PMSR_FTM_CAPA_ATTR_MIN_INTERVAL_NTB: u32 attribute indicating + * the minimum NTB ranging interval supported by the device + * in milli seconds. (0 means unknown). Applications can use this value + * to estimate the burst period to be given in the FTM request for the + * NTB ranging case. If non-zero, this value will be used to validate + * the nominal time in the FTM request. * * @NUM_NL80211_PMSR_FTM_CAPA_ATTR: internal * @NL80211_PMSR_FTM_CAPA_ATTR_MAX: highest attribute number @@ -8136,12 +8176,50 @@ enum nl80211_peer_measurement_ftm_capa { NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_TX, NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_RX, NL80211_PMSR_FTM_CAPA_ATTR_RSTA_SUPPORT, + NL80211_PMSR_FTM_CAPA_ATTR_ISTA_CAPS, + NL80211_PMSR_FTM_CAPA_ATTR_RSTA_CAPS, + NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_NTB, + NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_TB, + NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_EDCA, + NL80211_PMSR_FTM_CAPA_ATTR_TYPE_CAPS, + NL80211_PMSR_FTM_CAPA_ATTR_CONCURRENT_ISTA_RSTA_SUPPORT, + NL80211_PMSR_FTM_CAPA_ATTR_MAX_NUM_TX_ANTENNAS, + NL80211_PMSR_FTM_CAPA_ATTR_MAX_NUM_RX_ANTENNAS, + NL80211_PMSR_FTM_CAPA_ATTR_MIN_INTERVAL_EDCA, + NL80211_PMSR_FTM_CAPA_ATTR_MIN_INTERVAL_NTB, /* keep last */ NUM_NL80211_PMSR_FTM_CAPA_ATTR, NL80211_PMSR_FTM_CAPA_ATTR_MAX = NUM_NL80211_PMSR_FTM_CAPA_ATTR - 1 }; +/** + * enum nl80211_peer_measurement_ftm_type_capa - FTM ranging type capability + * sub-attributes, used inside %NL80211_PMSR_FTM_CAPA_ATTR_TYPE_CAPS + * @__NL80211_PMSR_FTM_TYPE_CAPA_ATTR_INVALID: invalid + * + * @NL80211_PMSR_FTM_TYPE_CAPA_ATTR_INFRA_SUPPORT: flag attribute indicating + * that the device supports infrastructure ranging (STA-to-AP or + * AP-to-STA) as part of Proximity Detection + * @NL80211_PMSR_FTM_TYPE_CAPA_ATTR_PD_SUPPORT: flag attribute indicating that + * the device supports peer-to-peer ranging as mentioned in the + * specification "PR Implementation Consideration Draft 1.9 rev 1" where + * PD stands for proximity detection + * + * @NUM_NL80211_PMSR_FTM_TYPE_CAPA_ATTR: internal + * @NL80211_PMSR_FTM_TYPE_CAPA_ATTR_MAX: highest attribute number + */ +enum nl80211_peer_measurement_ftm_type_capa { + __NL80211_PMSR_FTM_TYPE_CAPA_ATTR_INVALID, + + NL80211_PMSR_FTM_TYPE_CAPA_ATTR_INFRA_SUPPORT, + NL80211_PMSR_FTM_TYPE_CAPA_ATTR_PD_SUPPORT, + + /* keep last */ + NUM_NL80211_PMSR_FTM_TYPE_CAPA_ATTR, + NL80211_PMSR_FTM_TYPE_CAPA_ATTR_MAX = NUM_NL80211_PMSR_FTM_TYPE_CAPA_ATTR - 1 +}; + /** * enum nl80211_peer_measurement_ftm_req - FTM request attributes * @__NL80211_PMSR_FTM_REQ_ATTR_INVALID: invalid diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8e20fb714eff..0a87f4f81cd2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2503,10 +2503,97 @@ nl80211_send_pmsr_ftm_capa(const struct cfg80211_pmsr_capabilities *cap, nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_RX, cap->ftm.max_total_ltf_rx)) return -ENOBUFS; - if (cap->ftm.support_rsta && - nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_RSTA_SUPPORT)) + + if (cap->ftm.ista.support_ntb || cap->ftm.ista.support_tb || + cap->ftm.ista.support_edca) { + struct nlattr *ista_caps; + + ista_caps = nla_nest_start_noflag(msg, + NL80211_PMSR_FTM_CAPA_ATTR_ISTA_CAPS); + if (!ista_caps) + return -ENOBUFS; + if (cap->ftm.ista.support_ntb && + nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_NTB)) + return -ENOBUFS; + if (cap->ftm.ista.support_tb && + nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_TB)) + return -ENOBUFS; + if (cap->ftm.ista.support_edca && + nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_EDCA)) + return -ENOBUFS; + nla_nest_end(msg, ista_caps); + } + + if (cap->ftm.rsta.support_ntb || cap->ftm.rsta.support_tb || + cap->ftm.rsta.support_edca) { + struct nlattr *rsta_caps; + + /* + * Set the generic RSTA_SUPPORT flag if any of the specific + * ranging modes is supported to maintain the backward + * compatibility. + */ + if (nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_RSTA_SUPPORT)) + return -ENOBUFS; + + rsta_caps = nla_nest_start_noflag(msg, + NL80211_PMSR_FTM_CAPA_ATTR_RSTA_CAPS); + if (!rsta_caps) + return -ENOBUFS; + if (cap->ftm.rsta.support_ntb && + nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_NTB)) + return -ENOBUFS; + if (cap->ftm.rsta.support_tb && + nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_TB)) + return -ENOBUFS; + if (cap->ftm.rsta.support_edca && + nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_EDCA)) + return -ENOBUFS; + nla_nest_end(msg, rsta_caps); + } + + if (cap->ftm.max_no_of_tx_antennas && + nla_put_u8(msg, NL80211_PMSR_FTM_CAPA_ATTR_MAX_NUM_TX_ANTENNAS, + cap->ftm.max_no_of_tx_antennas)) + return -ENOBUFS; + + if (cap->ftm.max_no_of_rx_antennas && + nla_put_u8(msg, NL80211_PMSR_FTM_CAPA_ATTR_MAX_NUM_RX_ANTENNAS, + cap->ftm.max_no_of_rx_antennas)) + return -ENOBUFS; + + if (cap->ftm.min_allowed_ranging_interval_edca && + nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_MIN_INTERVAL_EDCA, + cap->ftm.min_allowed_ranging_interval_edca)) return -ENOBUFS; + if (cap->ftm.min_allowed_ranging_interval_ntb && + nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_MIN_INTERVAL_NTB, + cap->ftm.min_allowed_ranging_interval_ntb)) + return -ENOBUFS; + + if (cap->ftm.type.infra_support || cap->ftm.type.pd_support) { + struct nlattr *pd_caps; + + pd_caps = nla_nest_start_noflag(msg, + NL80211_PMSR_FTM_CAPA_ATTR_TYPE_CAPS); + if (!pd_caps) + return -ENOBUFS; + + if (cap->ftm.type.infra_support && + nla_put_flag(msg, NL80211_PMSR_FTM_TYPE_CAPA_ATTR_INFRA_SUPPORT)) + return -ENOBUFS; + + if (cap->ftm.type.pd_support && + nla_put_flag(msg, NL80211_PMSR_FTM_TYPE_CAPA_ATTR_PD_SUPPORT)) + return -ENOBUFS; + + nla_nest_end(msg, pd_caps); + } + + if (cap->ftm.concurrent_ista_rsta_support && + nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_CONCURRENT_ISTA_RSTA_SUPPORT)) + return -ENOBUFS; nla_nest_end(msg, ftm); return 0; } diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index afc0e3f931ec..c21f693fac29 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -188,10 +188,28 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, } out->ftm.rsta = !!tb[NL80211_PMSR_FTM_REQ_ATTR_RSTA]; - if (out->ftm.rsta && !capa->ftm.support_rsta) { + if (out->ftm.rsta && out->ftm.non_trigger_based && + !capa->ftm.rsta.support_ntb) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_RSTA], - "FTM: RSTA not supported by device"); + "FTM: NTB RSTA not supported by device"); + return -EOPNOTSUPP; + } + + if (out->ftm.rsta && out->ftm.trigger_based && + !capa->ftm.rsta.support_tb) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_FTM_REQ_ATTR_RSTA], + "FTM: TB RSTA not supported by device"); + return -EOPNOTSUPP; + } + + if (out->ftm.rsta && !out->ftm.non_trigger_based && + !out->ftm.trigger_based && + !capa->ftm.rsta.support_edca) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_FTM_REQ_ATTR_RSTA], + "FTM: EDCA RSTA not supported by device"); return -EOPNOTSUPP; } -- cgit v1.3-14-g43fede From 8823a9b0e7af5395cbfa06bf23806197d59cd124 Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:49 +0530 Subject: wifi: cfg80211: add NTB continuous ranging and FTM request type support Enable NTB continuous ranging with configurable timing and measurement parameters as per the Wi-Fi Alliance specification "Proximity Ranging (PR) Implementation Consideration Draft 1.9 Rev 1, section 5.3". Add new FTM request attributes for min/max time between measurements, nominal time (mandatory for NTB), AW duration, and total measurement count. Add NL80211_PMSR_PEER_ATTR_REQ_TYPE attribute using the new nl80211_peer_measurement_ftm_req_type enum to allow userspace to specify the ranging request type per peer: - NL80211_PMSR_FTM_REQ_TYPE_INFRA: STA-to-AP or AP-to-STA ranging (default if attribute is absent) - NL80211_PMSR_FTM_REQ_TYPE_PD: peer-to-peer ranging Validate the request type against the device TYPE_CAPS capabilities advertised via NL80211_PMSR_FTM_CAPA_ATTR_TYPE_CAPS. Reject PD requests if the device does not advertise PD support. Reject PD requests that set trigger-based ranging, as TB ranging is not compatible with peer-to-peer proximity detection. Add ftms_per_burst limit of 4 for PD NTB ranging requests. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-7-peddolla.reddy@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 35 ++++++++++++++++++++++++- include/uapi/linux/nl80211.h | 62 ++++++++++++++++++++++++++++++++++++++++++-- net/wireless/nl80211.c | 11 ++++++++ net/wireless/pmsr.c | 61 ++++++++++++++++++++++++++++++++++++++++--- 4 files changed, 163 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 98943a510112..28923539456e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4527,7 +4527,8 @@ struct cfg80211_pmsr_result { * @burst_duration: burst duration. If @trigger_based or @non_trigger_based is * set, this is the burst duration in milliseconds, and zero means the * device should pick an appropriate value based on @ftms_per_burst. - * @ftms_per_burst: number of FTMs per burst + * @ftms_per_burst: number of FTMs per burst. If set to 0, the firmware or + * driver can automatically select an appropriate value. * @ftmr_retries: number of retries for FTM request * @request_lci: request LCI information * @request_civicloc: request civic location information @@ -4544,6 +4545,31 @@ struct cfg80211_pmsr_result { * @bss_color: the bss color of the responder. Optional. Set to zero to * indicate the driver should set the BSS color. Only valid if * @non_trigger_based or @trigger_based is set. + * @request_type: ranging request type, one of + * &enum nl80211_peer_measurement_ftm_req_type. Defaults to + * %NL80211_PMSR_FTM_REQ_TYPE_INFRA if not specified. + * @min_time_between_measurements: minimum time between two consecutive range + * measurements in units of 100 microseconds, for non-trigger based + * ranging. Should be set as short as possible to minimize turnaround + * time, since two-way ranging with delayed LMR requires two measurements. + * Only valid if @non_trigger_based is set. + * @max_time_between_measurements: maximum time between two consecutive range + * measurements in units of 10 milliseconds, for non-trigger based + * ranging. Acts as a session timeout; if exceeded, the ranging session + * should be terminated. Only valid if @non_trigger_based is set. + * @availability_window: duration of the availability window (AW) in units of + * 1 millisecond (0-255 ms). Only valid if @non_trigger_based is set. + * If set to 0, the firmware or driver can automatically select an + * appropriate value. + * @nominal_time: Nominal duration between adjacent availability windows + * in units of milli seconds. Only valid if @non_trigger_based is set. + * If set to 0, the firmware or driver can automatically select an + * appropriate value. + * @num_measurements: number of Availability Windows (AWs) to schedule + * for non-trigger-based ranging. Each AW may contain multiple FTM + * exchanges as configured by @ftms_per_burst. Only valid if + * @non_trigger_based is set. If set to 0, the firmware or driver + * can automatically select an appropriate value. * * See also nl80211 for the respective attribute documentation. */ @@ -4563,6 +4589,13 @@ struct cfg80211_pmsr_ftm_request_peer { u8 ftms_per_burst; u8 ftmr_retries; u8 bss_color; + + u32 request_type; + u32 min_time_between_measurements; + u32 max_time_between_measurements; + u8 availability_window; + u32 nominal_time; + u32 num_measurements; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ea0acce724ca..6be89e656276 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -7991,6 +7991,26 @@ enum nl80211_peer_measurement_resp { NL80211_PMSR_RESP_ATTR_MAX = NUM_NL80211_PMSR_RESP_ATTRS - 1 }; +/** + * enum nl80211_peer_measurement_ftm_req_type - FTM ranging request type, + * used with %NL80211_PMSR_PEER_ATTR_REQ_TYPE + * + * @NL80211_PMSR_FTM_REQ_TYPE_INFRA: infrastructure ranging, i.e. STA-to-AP + * @NL80211_PMSR_FTM_REQ_TYPE_PD: peer-to-peer ranging as defined in the + * Wi-Fi Alliance specification "Proximity Ranging (PR) Implementation + * Consideration Draft 1.9 Rev 1" + * @NUM_NL80211_PMSR_FTM_REQ_TYPE: internal + * @NL80211_PMSR_FTM_REQ_TYPE_MAX: highest request type value + */ +enum nl80211_peer_measurement_ftm_req_type { + NL80211_PMSR_FTM_REQ_TYPE_INFRA, + NL80211_PMSR_FTM_REQ_TYPE_PD, + + /* keep last */ + NUM_NL80211_PMSR_FTM_REQ_TYPE, + NL80211_PMSR_FTM_REQ_TYPE_MAX = NUM_NL80211_PMSR_FTM_REQ_TYPE - 1 +}; + /** * enum nl80211_peer_measurement_peer_attrs - peer attributes for measurement * @__NL80211_PMSR_PEER_ATTR_INVALID: invalid @@ -8004,6 +8024,9 @@ enum nl80211_peer_measurement_resp { * @NL80211_PMSR_PEER_ATTR_RESP: This is a nested attribute indexed by * measurement type, with attributes from the * &enum nl80211_peer_measurement_resp inside. + * @NL80211_PMSR_PEER_ATTR_REQ_TYPE: u32 attribute specifying the ranging + * request type, using values from &enum nl80211_peer_measurement_ftm_req_type. + * If absent, defaults to %NL80211_PMSR_FTM_REQ_TYPE_INFRA. * * @NUM_NL80211_PMSR_PEER_ATTRS: internal * @NL80211_PMSR_PEER_ATTR_MAX: highest attribute number @@ -8015,6 +8038,7 @@ enum nl80211_peer_measurement_peer_attrs { NL80211_PMSR_PEER_ATTR_CHAN, NL80211_PMSR_PEER_ATTR_REQ, NL80211_PMSR_PEER_ATTR_RESP, + NL80211_PMSR_PEER_ATTR_REQ_TYPE, /* keep last */ NUM_NL80211_PMSR_PEER_ATTRS, @@ -8238,9 +8262,11 @@ enum nl80211_peer_measurement_ftm_type_capa { * default 15 i.e. "no preference"). For non-EDCA ranging, this is the * burst duration in milliseconds (optional with default 0, i.e. let the * device decide). - * @NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST: number of successful FTM frames - * requested per burst + * @NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST: (Optional) number of successful + * FTM frames requested per burst * (u8, 0-31, optional with default 0 i.e. "no preference") + * If the attribute is absent ("no preference"), the driver or firmware can + * choose a suitable value. * @NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES: number of FTMR frame retries * (u8, default 3) * @NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI: request LCI data (flag) @@ -8274,6 +8300,33 @@ enum nl80211_peer_measurement_ftm_type_capa { * Only valid if %NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK is set (so the * RSTA will have the measurement results to report back in the FTM * response). + * @NL80211_PMSR_FTM_REQ_ATTR_MIN_TIME_BETWEEN_MEASUREMENTS: minimum time + * between two consecutive range measurements in units of 100 microseconds, + * for non-trigger based ranging (u32). Should be set as short as possible + * to minimize turnaround time, since two-way ranging with delayed LMR + * requires two measurements. Only valid if + * %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set. + * @NL80211_PMSR_FTM_REQ_ATTR_MAX_TIME_BETWEEN_MEASUREMENTS: maximum time + * between two consecutive range measurements in units of 10 milliseconds, + * for non-trigger based ranging (u32). Acts as a session timeout; if + * exceeded, the ranging session should be terminated. Only valid if + * %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set. + * @NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME: The nominal time field shall be + * set to the nominal duration between adjacent Availability Windows in + * units of milli seconds (u32). Mandatory if + * %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set. + * @NL80211_PMSR_FTM_REQ_ATTR_AW_DURATION: (Optional) The AW duration field + * shall be set to the duration of the AW in units of 1ms (0-255 ms) (u32). + * Only valid if %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set. + * If the attribute is absent ("no preference"), the driver or firmware + * can choose a suitable value. + * @NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS: (Optional) number of + * Availability Windows (AWs) to schedule for non-trigger-based ranging. + * Each AW may contain multiple FTM exchanges as configured by + * %NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST. Only valid if + * %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set. + * If the attribute is absent ("no preference"), the driver or firmware + * can choose a suitable value. * * @NUM_NL80211_PMSR_FTM_REQ_ATTR: internal * @NL80211_PMSR_FTM_REQ_ATTR_MAX: highest attribute number @@ -8295,6 +8348,11 @@ enum nl80211_peer_measurement_ftm_req { NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK, NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR, NL80211_PMSR_FTM_REQ_ATTR_RSTA, + NL80211_PMSR_FTM_REQ_ATTR_MIN_TIME_BETWEEN_MEASUREMENTS, + NL80211_PMSR_FTM_REQ_ATTR_MAX_TIME_BETWEEN_MEASUREMENTS, + NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME, + NL80211_PMSR_FTM_REQ_ATTR_AW_DURATION, + NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS, /* keep last */ NUM_NL80211_PMSR_FTM_REQ_ATTR, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0a87f4f81cd2..61ecf8fceb6a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -476,6 +476,15 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_REQ_ATTR_RSTA] = { .type = NLA_FLAG }, + [NL80211_PMSR_FTM_REQ_ATTR_MIN_TIME_BETWEEN_MEASUREMENTS] = { + .type = NLA_U32 + }, + [NL80211_PMSR_FTM_REQ_ATTR_MAX_TIME_BETWEEN_MEASUREMENTS] = { + .type = NLA_U32 + }, + [NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME] = { .type = NLA_U32 }, + [NL80211_PMSR_FTM_REQ_ATTR_AW_DURATION] = NLA_POLICY_MAX(NLA_U32, 255), + [NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS] = { .type = NLA_U32 }, }; static const struct nla_policy @@ -498,6 +507,8 @@ nl80211_pmsr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { [NL80211_PMSR_PEER_ATTR_REQ] = NLA_POLICY_NESTED(nl80211_pmsr_req_attr_policy), [NL80211_PMSR_PEER_ATTR_RESP] = { .type = NLA_REJECT }, + [NL80211_PMSR_PEER_ATTR_REQ_TYPE] = + NLA_POLICY_MAX(NLA_U32, NL80211_PMSR_FTM_REQ_TYPE_MAX), }; static const struct nla_policy diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index c21f693fac29..951ba0b96da2 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -91,11 +91,10 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]); if (capa->ftm.max_ftms_per_burst && - (out->ftm.ftms_per_burst > capa->ftm.max_ftms_per_burst || - out->ftm.ftms_per_burst == 0)) { + out->ftm.ftms_per_burst > capa->ftm.max_ftms_per_burst) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST], - "FTM: FTMs per burst must be set lower than the device limit but non-zero"); + "FTM: FTMs per burst must be set lower than the device limit"); return -EINVAL; } @@ -128,6 +127,14 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, return -EINVAL; } + if (out->ftm.request_type == NL80211_PMSR_FTM_REQ_TYPE_PD && + out->ftm.trigger_based) { + NL_SET_ERR_MSG_ATTR(info->extack, + ftmreq, + "FTM: TB ranging is not supported for PD request type"); + return -EINVAL; + } + out->ftm.non_trigger_based = !!tb[NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED]; if (out->ftm.non_trigger_based && !capa->ftm.non_trigger_based) { @@ -143,6 +150,14 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, return -EINVAL; } + if (out->ftm.request_type == NL80211_PMSR_FTM_REQ_TYPE_PD && + out->ftm.non_trigger_based && out->ftm.ftms_per_burst > 4) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST], + "FTM: FTMs per burst must not exceed 4 for PD NTB ranging"); + return -ERANGE; + } + if (out->ftm.ftms_per_burst > 31 && !out->ftm.non_trigger_based && !out->ftm.trigger_based) { NL_SET_ERR_MSG_ATTR(info->extack, @@ -222,6 +237,33 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, return -EINVAL; } + if (out->ftm.non_trigger_based) { + if (out->ftm.request_type == NL80211_PMSR_FTM_REQ_TYPE_PD && + !tb[NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME]) { + NL_SET_ERR_MSG(info->extack, + "FTM: nominal time is required for PD NTB ranging"); + return -EINVAL; + } + out->ftm.nominal_time = + nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME]); + + if (tb[NL80211_PMSR_FTM_REQ_ATTR_MIN_TIME_BETWEEN_MEASUREMENTS]) + out->ftm.min_time_between_measurements = + nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_MIN_TIME_BETWEEN_MEASUREMENTS]); + + if (tb[NL80211_PMSR_FTM_REQ_ATTR_MAX_TIME_BETWEEN_MEASUREMENTS]) + out->ftm.max_time_between_measurements = + nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_MAX_TIME_BETWEEN_MEASUREMENTS]); + + if (tb[NL80211_PMSR_FTM_REQ_ATTR_AW_DURATION]) + out->ftm.availability_window = + nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_AW_DURATION]); + + if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS]) + out->ftm.num_measurements = + nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS]); + } + return 0; } @@ -249,6 +291,19 @@ static int pmsr_parse_peer(struct cfg80211_registered_device *rdev, memcpy(out->addr, nla_data(tb[NL80211_PMSR_PEER_ATTR_ADDR]), ETH_ALEN); + if (tb[NL80211_PMSR_PEER_ATTR_REQ_TYPE]) + out->ftm.request_type = + nla_get_u32(tb[NL80211_PMSR_PEER_ATTR_REQ_TYPE]); + else + out->ftm.request_type = NL80211_PMSR_FTM_REQ_TYPE_INFRA; + + if (out->ftm.request_type == NL80211_PMSR_FTM_REQ_TYPE_PD && + !rdev->wiphy.pmsr_capa->ftm.type.pd_support) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_PEER_ATTR_REQ_TYPE], + "FTM: PD request type not supported by device"); + return -EINVAL; + } /* reuse info->attrs */ memset(info->attrs, 0, sizeof(*info->attrs) * (NL80211_ATTR_MAX + 1)); err = nla_parse_nested_deprecated(info->attrs, NL80211_ATTR_MAX, -- cgit v1.3-14-g43fede From 4e901e99edd2c289e6917cb79027e39c98d711e2 Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:50 +0530 Subject: wifi: cfg80211: extend PMSR FTM response for proximity ranging Applications need negotiated session parameters to interpret proximity ranging results and perform post-processing. Currently, the FTM response lacks LTF repetition counts, time constraints, spatial stream configuration, and availability window parameters. Extend the FTM response structure to report these negotiated parameters, enabling applications to track session configuration and use them in post-processing to increase ranging precision. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-8-peddolla.reddy@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 56 ++++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/nl80211.h | 38 ++++++++++++++++++++++++++++++ net/wireless/pmsr.c | 15 ++++++++++++ 3 files changed, 107 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 28923539456e..ad32353e87e0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4436,6 +4436,25 @@ struct cfg80211_ftm_responder_stats { * (must have either this or @rtt_avg) * @dist_variance: variance of distances measured (see also @rtt_variance) * @dist_spread: spread of distances measured (see also @rtt_spread) + * @tx_ltf_repetition_count: negotiated value of number of tx ltf repetitions + * in NDP frames + * @rx_ltf_repetition_count: negotiated value of number of rx ltf repetitions + * in NDP frames + * @max_time_between_measurements: the negotiated maximum interval (in units of + * 10 ms) by which the ISTA must complete the next measurement cycle. + * @min_time_between_measurements: the negotiated minimum interval (in units of + * 100 us) between two consecutive range measurements initiated by the + * ISTA. + * @num_tx_spatial_streams: number of Tx space-time streams used in the NDP + * frame during the measurement sounding phase. + * @num_rx_spatial_streams: number of Rx space-time streams used in the NDP + * frame during the measurement sounding phase. + * @nominal_time: negotiated nominal duration between adjacent availability + * windows in units of milliseconds (u32). + * @availability_window: negotiated availability window time used in this + * session in units of milliseconds (u8). + * @chan_width: band width used for measurement. + * @preamble: preamble used for measurement. * @num_ftmr_attempts_valid: @num_ftmr_attempts is valid * @num_ftmr_successes_valid: @num_ftmr_successes is valid * @rssi_avg_valid: @rssi_avg is valid @@ -4448,6 +4467,18 @@ struct cfg80211_ftm_responder_stats { * @dist_avg_valid: @dist_avg is valid * @dist_variance_valid: @dist_variance is valid * @dist_spread_valid: @dist_spread is valid + * @tx_ltf_repetition_count_valid: @tx_ltf_repetition_count is valid + * @rx_ltf_repetition_count_valid: @rx_ltf_repetition_count is valid + * @max_time_between_measurements_valid: @max_time_between_measurements is valid + * @min_time_between_measurements_valid: @min_time_between_measurements is valid + * @num_tx_spatial_streams_valid: @num_tx_spatial_streams is valid + * @num_rx_spatial_streams_valid: @num_rx_spatial_streams is valid + * @nominal_time_valid: @nominal_time is valid + * @availability_window_valid: @availability_window is valid + * @chan_width_valid: @chan_width is valid. + * @preamble_valid: @preamble is valid. + * @is_delayed_lmr: indicates if the reported LMR is of the current burst or the + * previous burst, flag. */ struct cfg80211_pmsr_ftm_result { const u8 *lci; @@ -4471,8 +4502,18 @@ struct cfg80211_pmsr_ftm_result { s64 dist_avg; s64 dist_variance; s64 dist_spread; + u32 tx_ltf_repetition_count; + u32 rx_ltf_repetition_count; + u32 max_time_between_measurements; + u32 min_time_between_measurements; + u8 num_tx_spatial_streams; + u8 num_rx_spatial_streams; + u32 nominal_time; + u8 availability_window; + enum nl80211_chan_width chan_width; + enum nl80211_preamble preamble; - u16 num_ftmr_attempts_valid:1, + u32 num_ftmr_attempts_valid:1, num_ftmr_successes_valid:1, rssi_avg_valid:1, rssi_spread_valid:1, @@ -4483,7 +4524,18 @@ struct cfg80211_pmsr_ftm_result { rtt_spread_valid:1, dist_avg_valid:1, dist_variance_valid:1, - dist_spread_valid:1; + dist_spread_valid:1, + tx_ltf_repetition_count_valid:1, + rx_ltf_repetition_count_valid:1, + max_time_between_measurements_valid:1, + min_time_between_measurements_valid:1, + num_tx_spatial_streams_valid:1, + num_rx_spatial_streams_valid:1, + nominal_time_valid:1, + availability_window_valid:1, + chan_width_valid:1, + preamble_valid:1, + is_delayed_lmr:1; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6be89e656276..08e8e4de650c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -8439,6 +8439,33 @@ enum nl80211_peer_measurement_ftm_failure_reasons { * @NL80211_PMSR_FTM_RESP_ATTR_PAD: ignore, for u64/s64 padding only * @NL80211_PMSR_FTM_RESP_ATTR_BURST_PERIOD: actual burst period used by * the responder (similar to request, u16) + * @NL80211_PMSR_FTM_RESP_ATTR_TX_LTF_REPETITION_COUNT: negotiated value of + * number of tx ltf repetitions in NDP frames (u32, optional) + * @NL80211_PMSR_FTM_RESP_ATTR_RX_LTF_REPETITION_COUNT: negotiated value of + * number of rx ltf repetitions in NDP frames (u32, optional) + * @NL80211_PMSR_FTM_RESP_ATTR_MAX_TIME_BETWEEN_MEASUREMENTS: negotiated value + * where latest time by which the ISTA needs to complete the next round of + * measurements, in units of 10 ms (u32, optional) + * @NL80211_PMSR_FTM_RESP_ATTR_MIN_TIME_BETWEEN_MEASUREMENTS: negotiated + * minimum time between two consecutive range measurements initiated by an + * ISTA, in units of 100 us (u32, optional) + * @NL80211_PMSR_FTM_RESP_ATTR_NUM_TX_SPATIAL_STREAMS: number of Tx space-time + * streams used in NDP frames during the measurement sounding phase + * (u32, optional). + * @NL80211_PMSR_FTM_RESP_ATTR_NUM_RX_SPATIAL_STREAMS: number of Rx space-time + * streams used in the NDP frames during the measurement sounding phase + * (u32, optional) + * @NL80211_PMSR_FTM_RESP_ATTR_NOMINAL_TIME: negotiated nominal time used in + * this session in milliseconds. (u32, optional) + * @NL80211_PMSR_FTM_RESP_ATTR_AVAILABILITY_WINDOW: negotiated availability + * window time used in this session, in units of milli seconds. + * (u32, optional) + * @NL80211_PMSR_FTM_RESP_ATTR_CHANNEL_WIDTH: u32 attribute indicating channel + * width used for measurement, see &enum nl80211_chan_width (optional). + * @NL80211_PMSR_FTM_RESP_ATTR_PREAMBLE: u32 attribute indicating the preamble + * type used for the measurement, see &enum nl80211_preamble (optional). + * @NL80211_PMSR_FTM_RESP_ATTR_IS_DELAYED_LMR: flag, indicates if the + * current result is delayed LMR data. * * @NUM_NL80211_PMSR_FTM_RESP_ATTR: internal * @NL80211_PMSR_FTM_RESP_ATTR_MAX: highest attribute number @@ -8468,6 +8495,17 @@ enum nl80211_peer_measurement_ftm_resp { NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC, NL80211_PMSR_FTM_RESP_ATTR_PAD, NL80211_PMSR_FTM_RESP_ATTR_BURST_PERIOD, + NL80211_PMSR_FTM_RESP_ATTR_TX_LTF_REPETITION_COUNT, + NL80211_PMSR_FTM_RESP_ATTR_RX_LTF_REPETITION_COUNT, + NL80211_PMSR_FTM_RESP_ATTR_MAX_TIME_BETWEEN_MEASUREMENTS, + NL80211_PMSR_FTM_RESP_ATTR_MIN_TIME_BETWEEN_MEASUREMENTS, + NL80211_PMSR_FTM_RESP_ATTR_NUM_TX_SPATIAL_STREAMS, + NL80211_PMSR_FTM_RESP_ATTR_NUM_RX_SPATIAL_STREAMS, + NL80211_PMSR_FTM_RESP_ATTR_NOMINAL_TIME, + NL80211_PMSR_FTM_RESP_ATTR_AVAILABILITY_WINDOW, + NL80211_PMSR_FTM_RESP_ATTR_CHANNEL_WIDTH, + NL80211_PMSR_FTM_RESP_ATTR_PREAMBLE, + NL80211_PMSR_FTM_RESP_ATTR_IS_DELAYED_LMR, /* keep last */ NUM_NL80211_PMSR_FTM_RESP_ATTR, diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 951ba0b96da2..caffa2421c20 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -562,6 +562,21 @@ static int nl80211_pmsr_send_ftm_res(struct sk_buff *msg, PUTOPT_U64(DIST_AVG, dist_avg); PUTOPT_U64(DIST_VARIANCE, dist_variance); PUTOPT_U64(DIST_SPREAD, dist_spread); + PUTOPT(u32, TX_LTF_REPETITION_COUNT, tx_ltf_repetition_count); + PUTOPT(u32, RX_LTF_REPETITION_COUNT, rx_ltf_repetition_count); + PUTOPT(u32, MAX_TIME_BETWEEN_MEASUREMENTS, + max_time_between_measurements); + PUTOPT(u32, MIN_TIME_BETWEEN_MEASUREMENTS, + min_time_between_measurements); + PUTOPT(u8, NUM_TX_SPATIAL_STREAMS, num_tx_spatial_streams); + PUTOPT(u8, NUM_RX_SPATIAL_STREAMS, num_rx_spatial_streams); + PUTOPT(u32, NOMINAL_TIME, nominal_time); + PUTOPT(u8, AVAILABILITY_WINDOW, availability_window); + PUTOPT(u32, CHANNEL_WIDTH, chan_width); + PUTOPT(u32, PREAMBLE, preamble); + if (res->ftm.is_delayed_lmr && + nla_put_flag(msg, NL80211_PMSR_FTM_RESP_ATTR_IS_DELAYED_LMR)) + goto error; if (res->ftm.lci && res->ftm.lci_len && nla_put(msg, NL80211_PMSR_FTM_RESP_ATTR_LCI, res->ftm.lci_len, res->ftm.lci)) -- cgit v1.3-14-g43fede From ea996c2c036df21fbd3b195e6c5c42c11eadb6c4 Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:51 +0530 Subject: wifi: cfg80211: add role-based peer limits to FTM capabilities Peer measurement capabilities currently advertise a single maximum peer count regardless of device role. Some devices support different peer limits when operating as initiator versus responder. Add max_peers fields inside the ftm.ista and ftm.rsta sub-structs of cfg80211_pmsr_capabilities to allow drivers to advertise per-role peer limits. These limits are generic and not restricted to any specific ranging type. Expose these over nl80211 using new NL80211_PMSR_ATTR_MAX_PEER_ISTA_ROLE and NL80211_PMSR_ATTR_MAX_PEER_RSTA_ROLE attributes inside the ISTA_CAPS and RSTA_CAPS nested attributes respectively. When a role limit is advertised, validate the number of peers in the request separately for each role using the existing rsta flag in the FTM request, and reject the request if the limit is exceeded. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-9-peddolla.reddy@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 6 ++++++ include/uapi/linux/nl80211.h | 14 ++++++++++++++ net/wireless/nl80211.c | 8 ++++++++ net/wireless/pmsr.c | 46 ++++++++++++++++++++++++++++++++++++++++---- 4 files changed, 70 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ad32353e87e0..5669948e0f3d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6003,6 +6003,8 @@ cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); * TB ranging. * @ftm.ista.support_edca: supports operating as ISTA in PMSR FTM request for * EDCA based ranging. + * @ftm.ista.max_peers: maximum number of peers supported in the ISTA role. + * If zero, no role-specific peer limit applies. * @ftm.rsta: responder role capabilities * @ftm.rsta.support_ntb: supports operating as RSTA in PMSR FTM request for * NTB ranging. @@ -6010,6 +6012,8 @@ cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); * TB ranging. * @ftm.rsta.support_edca: supports operating as RSTA in PMSR FTM request for * EDCA based ranging. + * @ftm.rsta.max_peers: maximum number of peers supported in the RSTA role. + * If zero, no role-specific peer limit applies. * @ftm.max_no_of_tx_antennas: maximum number of transmit antennas supported for * EDCA based ranging (0 means unknown) * @ftm.max_no_of_rx_antennas: maximum number of receive antennas supported for @@ -6064,11 +6068,13 @@ struct cfg80211_pmsr_capabilities { u8 support_ntb:1, support_tb:1, support_edca:1; + u32 max_peers; } ista; struct { u8 support_ntb:1, support_tb:1, support_edca:1; + u32 max_peers; } rsta; u8 max_no_of_tx_antennas; u8 max_no_of_rx_antennas; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 08e8e4de650c..e31ff2a745b2 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -8065,6 +8065,18 @@ enum nl80211_peer_measurement_peer_attrs { * meaningless, just a list of peers to measure with, with the * sub-attributes taken from * &enum nl80211_peer_measurement_peer_attrs. + * @NL80211_PMSR_ATTR_MAX_PEER_ISTA_ROLE: u32 attribute indicating the + * maximum number of peers supported when the device operates in the + * ISTA (Initiator STA) role. If absent, no role-specific peer limit + * applies. The sum of %NL80211_PMSR_ATTR_MAX_PEER_ISTA_ROLE and + * %NL80211_PMSR_ATTR_MAX_PEER_RSTA_ROLE is enforced when the device + * supports concurrent ISTA/RSTA operation. + * @NL80211_PMSR_ATTR_MAX_PEER_RSTA_ROLE: u32 attribute indicating the + * maximum number of peers supported when the device operates in the + * RSTA (Responder STA) role. If absent, no role-specific peer limit + * applies. The sum of %NL80211_PMSR_ATTR_MAX_PEER_ISTA_ROLE and + * %NL80211_PMSR_ATTR_MAX_PEER_RSTA_ROLE is enforced when the device + * supports concurrent ISTA/RSTA operation. * * @NUM_NL80211_PMSR_ATTR: internal * @NL80211_PMSR_ATTR_MAX: highest attribute number @@ -8077,6 +8089,8 @@ enum nl80211_peer_measurement_attrs { NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR, NL80211_PMSR_ATTR_TYPE_CAPA, NL80211_PMSR_ATTR_PEERS, + NL80211_PMSR_ATTR_MAX_PEER_ISTA_ROLE, + NL80211_PMSR_ATTR_MAX_PEER_RSTA_ROLE, /* keep last */ NUM_NL80211_PMSR_ATTR, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 61ecf8fceb6a..0ffaa2cd7808 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2532,6 +2532,10 @@ nl80211_send_pmsr_ftm_capa(const struct cfg80211_pmsr_capabilities *cap, if (cap->ftm.ista.support_edca && nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_EDCA)) return -ENOBUFS; + if (cap->ftm.ista.max_peers && + nla_put_u32(msg, NL80211_PMSR_ATTR_MAX_PEER_ISTA_ROLE, + cap->ftm.ista.max_peers)) + return -ENOBUFS; nla_nest_end(msg, ista_caps); } @@ -2560,6 +2564,10 @@ nl80211_send_pmsr_ftm_capa(const struct cfg80211_pmsr_capabilities *cap, if (cap->ftm.rsta.support_edca && nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_SUPPORT_EDCA)) return -ENOBUFS; + if (cap->ftm.rsta.max_peers && + nla_put_u32(msg, NL80211_PMSR_ATTR_MAX_PEER_RSTA_ROLE, + cap->ftm.rsta.max_peers)) + return -ENOBUFS; nla_nest_end(msg, rsta_caps); } diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index caffa2421c20..432d34be7945 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -361,12 +361,15 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) { struct nlattr *reqattr = info->attrs[NL80211_ATTR_PEER_MEASUREMENTS]; struct cfg80211_registered_device *rdev = info->user_ptr[0]; + int count, rem, err, idx, peer_count; struct wireless_dev *wdev = info->user_ptr[1]; + const struct cfg80211_pmsr_capabilities *capa; struct cfg80211_pmsr_request *req; struct nlattr *peers, *peer; - int count, rem, err, idx; - if (!rdev->wiphy.pmsr_capa) + capa = rdev->wiphy.pmsr_capa; + + if (!capa) return -EOPNOTSUPP; if (!reqattr) @@ -381,7 +384,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(peer, peers, rem) { count++; - if (count > rdev->wiphy.pmsr_capa->max_peers) { + if (count > capa->max_peers) { NL_SET_ERR_MSG_ATTR(info->extack, peer, "Too many peers used"); return -EINVAL; @@ -397,7 +400,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) req->timeout = nla_get_u32(info->attrs[NL80211_ATTR_TIMEOUT]); if (info->attrs[NL80211_ATTR_MAC]) { - if (!rdev->wiphy.pmsr_capa->randomize_mac_addr) { + if (!capa->randomize_mac_addr) { NL_SET_ERR_MSG_ATTR(info->extack, info->attrs[NL80211_ATTR_MAC], "device cannot randomize MAC address"); @@ -422,6 +425,41 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) goto out_err; idx++; } + + /* Validate per-role peer limits if advertised */ + if (capa->ftm.ista.max_peers) { + peer_count = 0; + + for (idx = 0; idx < req->n_peers; idx++) { + if (!req->peers[idx].ftm.rsta) { + peer_count++; + + if (peer_count > capa->ftm.ista.max_peers) { + NL_SET_ERR_MSG(info->extack, + "Too many ISTA peers for device limit"); + err = -EINVAL; + goto out_err; + } + } + } + } + + if (capa->ftm.rsta.max_peers) { + peer_count = 0; + + for (idx = 0; idx < req->n_peers; idx++) { + if (req->peers[idx].ftm.rsta) { + peer_count++; + + if (peer_count > capa->ftm.rsta.max_peers) { + NL_SET_ERR_MSG(info->extack, + "Too many RSTA peers for device limit"); + err = -EINVAL; + goto out_err; + } + } + } + } req->cookie = cfg80211_assign_cookie(rdev); req->nl_portid = info->snd_portid; -- cgit v1.3-14-g43fede From 99529edd28df505576366753e204ba78a406659b Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:52 +0530 Subject: wifi: cfg80211: add ingress/egress distance thresholds for FTM Proximity detection applications need to receive measurement results only when devices cross specific distance boundaries to avoid unnecessary host wakeups and reduce power consumption. Introduce configurable distance-based reporting thresholds that drivers can use to implement selective result reporting. Add ingress and egress distance parameters allowing applications to specify when results should be reported as peers cross these boundaries. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-10-peddolla.reddy@oss.qualcomm.com [remove mm units from variables] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 14 ++++++++++++++ include/uapi/linux/nl80211.h | 15 +++++++++++++++ net/wireless/nl80211.c | 2 ++ net/wireless/pmsr.c | 8 ++++++++ 4 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5669948e0f3d..87e848750339 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4622,6 +4622,18 @@ struct cfg80211_pmsr_result { * exchanges as configured by @ftms_per_burst. Only valid if * @non_trigger_based is set. If set to 0, the firmware or driver * can automatically select an appropriate value. + * @ingress_distance: optional ingress threshold in units of mm. When set, + * the measurement result of the peer needs to be indicated if the device + * moves into this range. Measurement results need to be sent on a burst + * index basis in this case. + * @egress_distance: optional egress threshold in units of mm. When set, + * the measurement result of the peer needs to be indicated if the device + * moves out of this range. Measurement results need to be sent on a burst + * index basis in this case. + * If neither or only one of @ingress_distance and @egress_distance + * is set, only the specified threshold is used. If both are set, both + * thresholds are applied. If neither is set, results are reported without + * threshold filtering. * * See also nl80211 for the respective attribute documentation. */ @@ -4648,6 +4660,8 @@ struct cfg80211_pmsr_ftm_request_peer { u8 availability_window; u32 nominal_time; u32 num_measurements; + u64 ingress_distance; + u64 egress_distance; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e31ff2a745b2..02fe42b4f29c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -8341,6 +8341,18 @@ enum nl80211_peer_measurement_ftm_type_capa { * %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set. * If the attribute is absent ("no preference"), the driver or firmware * can choose a suitable value. + * @NL80211_PMSR_FTM_REQ_ATTR_PAD: ignore, for u64/s64 padding only. + * @NL80211_PMSR_FTM_REQ_ATTR_INGRESS: optional u64 attribute in units of mm. + * When specified, the measurement result of the peer needs to be + * indicated if the device moves into this range. + * @NL80211_PMSR_FTM_REQ_ATTR_EGRESS: optional u64 attribute in units of mm. + * When specified, the measurement result of the peer needs to be + * indicated if the device moves out of this range. + * If neither or only one of @NL80211_PMSR_FTM_REQ_ATTR_INGRESS and + * @NL80211_PMSR_FTM_REQ_ATTR_EGRESS is specified, only the specified + * threshold is used. If both are specified, both thresholds are applied. + * If neither is specified, results are reported without threshold + * filtering. * * @NUM_NL80211_PMSR_FTM_REQ_ATTR: internal * @NL80211_PMSR_FTM_REQ_ATTR_MAX: highest attribute number @@ -8367,6 +8379,9 @@ enum nl80211_peer_measurement_ftm_req { NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME, NL80211_PMSR_FTM_REQ_ATTR_AW_DURATION, NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS, + NL80211_PMSR_FTM_REQ_ATTR_PAD, + NL80211_PMSR_FTM_REQ_ATTR_INGRESS, + NL80211_PMSR_FTM_REQ_ATTR_EGRESS, /* keep last */ NUM_NL80211_PMSR_FTM_REQ_ATTR, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0ffaa2cd7808..ae968d53fcea 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -485,6 +485,8 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_NOMINAL_TIME] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_REQ_ATTR_AW_DURATION] = NLA_POLICY_MAX(NLA_U32, 255), [NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS] = { .type = NLA_U32 }, + [NL80211_PMSR_FTM_REQ_ATTR_INGRESS] = { .type = NLA_U64 }, + [NL80211_PMSR_FTM_REQ_ATTR_EGRESS] = { .type = NLA_U64 }, }; static const struct nla_policy diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 432d34be7945..2d6ace7f048d 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -264,6 +264,14 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS]); } + if (tb[NL80211_PMSR_FTM_REQ_ATTR_INGRESS]) + out->ftm.ingress_distance = + nla_get_u64(tb[NL80211_PMSR_FTM_REQ_ATTR_INGRESS]); + + if (tb[NL80211_PMSR_FTM_REQ_ATTR_EGRESS]) + out->ftm.egress_distance = + nla_get_u64(tb[NL80211_PMSR_FTM_REQ_ATTR_EGRESS]); + return 0; } -- cgit v1.3-14-g43fede From 5733daa670dc1e1464be59dfcacaa76597201b3e Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:53 +0530 Subject: wifi: cfg80211: add PD-specific preamble and bandwidth capabilities Devices may support different preamble and bandwidth configurations for proximity detection (PD) ranging versus standard ranging. Add separate pd_preambles and pd_bandwidths fields to cfg80211_pmsr_capabilities to allow drivers to advertise PD-specific capabilities. Expose these over nl80211 using new attributes NL80211_PMSR_FTM_CAPA_ATTR_PD_PREAMBLES and NL80211_PMSR_FTM_CAPA_ATTR_PD_BANDWIDTHS, advertised only when pd_support is set. For PD requests, validate bandwidth and preamble against pd_bandwidths and pd_preambles. For non-PD requests, validate against the existing bandwidths and preambles fields. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-11-peddolla.reddy@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 6 ++++++ include/uapi/linux/nl80211.h | 10 ++++++++++ net/wireless/nl80211.c | 12 ++++++++++++ net/wireless/pmsr.c | 21 +++++++++++++++++++-- 4 files changed, 47 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 87e848750339..f5a47a0c7532 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6053,6 +6053,10 @@ cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); * @ftm.concurrent_ista_rsta_support: indicates if the device can * simultaneously act as initiator and responder in a multi-peer * measurement request. Only valid if @ftm.rsta_support is set. + * @ftm.pd_preambles: bitmap of preambles supported (&enum nl80211_preamble) + * for PD ranging requests. Ignored if @ftm.type.pd_support is not set. + * @ftm.pd_bandwidths: bitmap of bandwidths supported (&enum nl80211_chan_width) + * for PD ranging requests. Ignored if @ftm.type.pd_support is not set. */ struct cfg80211_pmsr_capabilities { unsigned int max_peers; @@ -6099,6 +6103,8 @@ struct cfg80211_pmsr_capabilities { pd_support:1; } type; u8 concurrent_ista_rsta_support:1; + u32 pd_preambles; + u32 pd_bandwidths; } ftm; }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 02fe42b4f29c..5bef8fd25270 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -8189,6 +8189,14 @@ enum nl80211_peer_measurement_attrs { * to estimate the burst period to be given in the FTM request for the * NTB ranging case. If non-zero, this value will be used to validate * the nominal time in the FTM request. + * @NL80211_PMSR_FTM_CAPA_ATTR_PD_PREAMBLES: u32 bitmap of values from + * &enum nl80211_preamble indicating the supported preambles for PD + * ranging requests. Only valid if %NL80211_PMSR_FTM_TYPE_CAPA_ATTR_PD_SUPPORT + * is set. + * @NL80211_PMSR_FTM_CAPA_ATTR_PD_BANDWIDTHS: u32 bitmap of values from + * &enum nl80211_chan_width indicating the supported channel bandwidths + * for PD ranging requests. Only valid if + * %NL80211_PMSR_FTM_TYPE_CAPA_ATTR_PD_SUPPORT is set. * * @NUM_NL80211_PMSR_FTM_CAPA_ATTR: internal * @NL80211_PMSR_FTM_CAPA_ATTR_MAX: highest attribute number @@ -8225,6 +8233,8 @@ enum nl80211_peer_measurement_ftm_capa { NL80211_PMSR_FTM_CAPA_ATTR_MAX_NUM_RX_ANTENNAS, NL80211_PMSR_FTM_CAPA_ATTR_MIN_INTERVAL_EDCA, NL80211_PMSR_FTM_CAPA_ATTR_MIN_INTERVAL_NTB, + NL80211_PMSR_FTM_CAPA_ATTR_PD_PREAMBLES, + NL80211_PMSR_FTM_CAPA_ATTR_PD_BANDWIDTHS, /* keep last */ NUM_NL80211_PMSR_FTM_CAPA_ATTR, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ae968d53fcea..84f17032fdd9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2615,6 +2615,18 @@ nl80211_send_pmsr_ftm_capa(const struct cfg80211_pmsr_capabilities *cap, if (cap->ftm.concurrent_ista_rsta_support && nla_put_flag(msg, NL80211_PMSR_FTM_CAPA_ATTR_CONCURRENT_ISTA_RSTA_SUPPORT)) return -ENOBUFS; + + if (cap->ftm.type.pd_support) { + if (cap->ftm.pd_preambles && + nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_PD_PREAMBLES, + cap->ftm.pd_preambles)) + return -ENOBUFS; + if (cap->ftm.pd_bandwidths && + nla_put_u32(msg, NL80211_PMSR_FTM_CAPA_ATTR_PD_BANDWIDTHS, + cap->ftm.pd_bandwidths)) + return -ENOBUFS; + } + nla_nest_end(msg, ftm); return 0; } diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 2d6ace7f048d..8b7843f75db2 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -17,11 +17,19 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, u32 preamble = NL80211_PREAMBLE_DMG; /* only optional in DMG */ /* validate existing data */ - if (!(rdev->wiphy.pmsr_capa->ftm.bandwidths & BIT(out->chandef.width))) { + if (out->ftm.request_type == NL80211_PMSR_FTM_REQ_TYPE_INFRA && + !(capa->ftm.bandwidths & BIT(out->chandef.width))) { NL_SET_ERR_MSG(info->extack, "FTM: unsupported bandwidth"); return -EINVAL; } + if (out->ftm.request_type == NL80211_PMSR_FTM_REQ_TYPE_PD && + !(capa->ftm.pd_bandwidths & BIT(out->chandef.width))) { + NL_SET_ERR_MSG(info->extack, + "FTM: unsupported bandwidth for PD request"); + return -EINVAL; + } + /* no validation needed - was already done via nested policy */ nla_parse_nested_deprecated(tb, NL80211_PMSR_FTM_REQ_ATTR_MAX, ftmreq, NULL, NULL); @@ -44,13 +52,22 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, } } - if (!(capa->ftm.preambles & BIT(preamble))) { + if (out->ftm.request_type == NL80211_PMSR_FTM_REQ_TYPE_INFRA && + !(capa->ftm.preambles & BIT(preamble))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE], "FTM: invalid preamble"); return -EINVAL; } + if (out->ftm.request_type == NL80211_PMSR_FTM_REQ_TYPE_PD && + !(capa->ftm.pd_preambles & BIT(preamble))) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE], + "FTM: invalid preamble for PD request"); + return -EINVAL; + } + out->ftm.preamble = preamble; out->ftm.burst_period = 0; -- cgit v1.3-14-g43fede From 410aa47fd9d308029f3520e97eec71a8eb508622 Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:54 +0530 Subject: wifi: cfg80211: allow suppressing FTM result reporting for PD requests Proximity detection often does not require detailed ranging measurements, yet userspace currently receives full FTM results for every request, causing unnecessary data transfer, host wakeups, and processing overhead. Add an optional control to suppress ranging result reporting for peer-to-peer PD requests. Introduce the NL80211_PMSR_FTM_REQ_ATTR_PD_SUPPRESS_RESULTS flag; when set with a PD request, the device may perform the measurements (e.g. when acting as RSTA) but must not report the measurement results to userspace. Validate that the flag is only accepted when request_type is set to NL80211_PMSR_FTM_REQ_TYPE_PD, reject otherwise. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-12-peddolla.reddy@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 6 ++++++ include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/nl80211.c | 1 + net/wireless/pmsr.c | 11 +++++++++++ 4 files changed, 24 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f5a47a0c7532..fdc8363b296c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4634,6 +4634,11 @@ struct cfg80211_pmsr_result { * is set, only the specified threshold is used. If both are set, both * thresholds are applied. If neither is set, results are reported without * threshold filtering. + * @pd_suppress_range_results: flag to suppress ranging results for PD + * requests. When set, the device performs ranging measurements to + * provide ranging services to a peer (e.g. in RSTA role) but does + * not report the measurement results to userspace. Only valid when + * @request_type is %NL80211_PMSR_FTM_REQ_TYPE_PD. * * See also nl80211 for the respective attribute documentation. */ @@ -4662,6 +4667,7 @@ struct cfg80211_pmsr_ftm_request_peer { u32 num_measurements; u64 ingress_distance; u64 egress_distance; + u8 pd_suppress_range_results:1; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5bef8fd25270..1da4dc3fc816 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -8363,6 +8363,11 @@ enum nl80211_peer_measurement_ftm_type_capa { * threshold is used. If both are specified, both thresholds are applied. * If neither is specified, results are reported without threshold * filtering. + * @NL80211_PMSR_FTM_REQ_ATTR_PD_SUPPRESS_RESULTS: Flag to suppress ranging + * results for PD requests. When set, ranging measurements are performed + * but results are not reported to userspace, regardless of ranging role + * or type. Only valid when %NL80211_PMSR_PEER_ATTR_REQ_TYPE is set to + * %NL80211_PMSR_FTM_REQ_TYPE_PD. * * @NUM_NL80211_PMSR_FTM_REQ_ATTR: internal * @NL80211_PMSR_FTM_REQ_ATTR_MAX: highest attribute number @@ -8392,6 +8397,7 @@ enum nl80211_peer_measurement_ftm_req { NL80211_PMSR_FTM_REQ_ATTR_PAD, NL80211_PMSR_FTM_REQ_ATTR_INGRESS, NL80211_PMSR_FTM_REQ_ATTR_EGRESS, + NL80211_PMSR_FTM_REQ_ATTR_PD_SUPPRESS_RESULTS, /* keep last */ NUM_NL80211_PMSR_FTM_REQ_ATTR, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 84f17032fdd9..b33f688b983a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -487,6 +487,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_NUM_MEASUREMENTS] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_REQ_ATTR_INGRESS] = { .type = NLA_U64 }, [NL80211_PMSR_FTM_REQ_ATTR_EGRESS] = { .type = NLA_U64 }, + [NL80211_PMSR_FTM_REQ_ATTR_PD_SUPPRESS_RESULTS] = { .type = NLA_FLAG }, }; static const struct nla_policy diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 8b7843f75db2..f77658b6fccc 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -289,6 +289,17 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.egress_distance = nla_get_u64(tb[NL80211_PMSR_FTM_REQ_ATTR_EGRESS]); + out->ftm.pd_suppress_range_results = + nla_get_flag(tb[NL80211_PMSR_FTM_REQ_ATTR_PD_SUPPRESS_RESULTS]); + + if (out->ftm.request_type != NL80211_PMSR_FTM_REQ_TYPE_PD && + out->ftm.pd_suppress_range_results) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_FTM_REQ_ATTR_PD_SUPPRESS_RESULTS], + "FTM: suppress range result flag only valid for PD requests"); + return -EINVAL; + } + return 0; } -- cgit v1.3-14-g43fede From 4bb6e58bc29ab772c26c5eb471ab255fe2e044d8 Mon Sep 17 00:00:00 2001 From: Peddolla Harshavardhan Reddy Date: Mon, 20 Apr 2026 14:38:55 +0530 Subject: wifi: cfg80211: add LTF keyseed support for secure ranging Currently there is no way to install an LTF key seed that can be used in non-trigger-based (NTB) and trigger-based (TB) FTM ranging to protect NDP frames. Without this, drivers cannot enable PHY-layer security for peer measurement sessions, leaving ranging measurements vulnerable to eavesdropping and manipulation. Introduce NL80211_KEY_LTF_SEED attribute and the dedicated extended feature flag NL80211_EXT_FEATURE_SET_KEY_LTF_SEED to allow drivers to advertise and install LTF key seeds via nl80211. The key seed must be configured beforehand to ensure the peer measurement session is secure. The driver must advertise both NL80211_EXT_FEATURE_SECURE_LTF and NL80211_EXT_FEATURE_SET_KEY_LTF_SEED for the key seed installation to be permitted. The LTF key seed is pairwise key material and must only be used with pairwise key type. Reject attempts to use it with other key types. Signed-off-by: Peddolla Harshavardhan Reddy Link: https://patch.msgid.link/20260420090856.2152905-13-peddolla.reddy@oss.qualcomm.com [fix policy coding style] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 18 ++++++++++++++++++ net/wireless/nl80211.c | 9 +++++++++ net/wireless/util.c | 15 +++++++++++++++ 5 files changed, 47 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 23f9df9be837..11106589acc6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2236,6 +2236,7 @@ struct ieee80211_multiple_bssid_configuration { #define WLAN_AKM_SUITE_WFA_DPP SUITE(WLAN_OUI_WFA, 2) #define WLAN_MAX_KEY_LEN 32 +#define WLAN_MAX_SECURE_LTF_KEYSEED_LEN 48 #define WLAN_PMK_NAME_LEN 16 #define WLAN_PMKID_LEN 16 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index fdc8363b296c..13e035fecf7f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -830,6 +830,8 @@ struct vif_params { * @seq_len: length of @seq. * @vlan_id: vlan_id for VLAN group key (if nonzero) * @mode: key install mode (RX_TX, NO_TX or SET_TX) + * @ltf_keyseed: LTF key seed material + * @ltf_keyseed_len: length of LTF key seed material */ struct key_params { const u8 *key; @@ -839,6 +841,8 @@ struct key_params { u16 vlan_id; u32 cipher; enum nl80211_key_mode mode; + const u8 *ltf_keyseed; + size_t ltf_keyseed_len; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 1da4dc3fc816..6c7e6c05b9a8 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5814,6 +5814,18 @@ enum nl80211_key_default_types { * @NL80211_KEY_MODE: the mode from enum nl80211_key_mode. * Defaults to @NL80211_KEY_RX_TX. * @NL80211_KEY_DEFAULT_BEACON: flag indicating default Beacon frame key + * @NL80211_KEY_LTF_SEED: LTF key seed is used by the driver to generate + * secure LTF keys used in case of peer measurement request with FTM + * request type as either %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED + * or %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED. Secure LTF key seeds + * will help enable PHY security in peer measurement session. + * The LTF key seed is installed along with the TK (Temporal Key) using + * %NL80211_CMD_NEW_KEY. The TK is configured using the + * %NL80211_ATTR_KEY_DATA attribute, while the LTF key seed is configured + * using this attribute. Both keys must be configured before initiation + * of peer measurement to ensure peer measurement session is secure. + * Only valid if %NL80211_EXT_FEATURE_SET_KEY_LTF_SEED is set. This + * attribute is restricted to pairwise keys (%NL80211_KEYTYPE_PAIRWISE). * * @__NL80211_KEY_AFTER_LAST: internal * @NL80211_KEY_MAX: highest key attribute @@ -5830,6 +5842,7 @@ enum nl80211_key_attributes { NL80211_KEY_DEFAULT_TYPES, NL80211_KEY_MODE, NL80211_KEY_DEFAULT_BEACON, + NL80211_KEY_LTF_SEED, /* keep last */ __NL80211_KEY_AFTER_LAST, @@ -7059,6 +7072,10 @@ enum nl80211_feature_flags { * forward frames with a matching MAC address to userspace during * the off-channel period. * + * @NL80211_EXT_FEATURE_SET_KEY_LTF_SEED: Driver supports installing the + * LTF key seed via %NL80211_KEY_LTF_SEED. The seed is used to generate + * secure LTF keys for secure LTF measurement sessions. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -7139,6 +7156,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_ASSOC_FRAME_ENCRYPTION, NL80211_EXT_FEATURE_IEEE8021X_AUTH, NL80211_EXT_FEATURE_ROC_ADDR_FILTER, + NL80211_EXT_FEATURE_SET_KEY_LTF_SEED, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b33f688b983a..61b1716daf1e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1103,6 +1103,10 @@ static const struct nla_policy nl80211_key_policy[NL80211_KEY_MAX + 1] = { [NL80211_KEY_TYPE] = NLA_POLICY_MAX(NLA_U32, NUM_NL80211_KEYTYPES - 1), [NL80211_KEY_DEFAULT_TYPES] = { .type = NLA_NESTED }, [NL80211_KEY_MODE] = NLA_POLICY_RANGE(NLA_U8, 0, NL80211_KEY_SET_TX), + [NL80211_KEY_LTF_SEED] = { + .type = NLA_BINARY, + .len = WLAN_MAX_SECURE_LTF_KEYSEED_LEN, + }, }; /* policy for the key default flags */ @@ -1634,6 +1638,11 @@ static int nl80211_parse_key_new(struct genl_info *info, struct nlattr *key, if (tb[NL80211_KEY_MODE]) k->p.mode = nla_get_u8(tb[NL80211_KEY_MODE]); + if (tb[NL80211_KEY_LTF_SEED]) { + k->p.ltf_keyseed = nla_data(tb[NL80211_KEY_LTF_SEED]); + k->p.ltf_keyseed_len = nla_len(tb[NL80211_KEY_LTF_SEED]); + } + return 0; } diff --git a/net/wireless/util.c b/net/wireless/util.c index b638e205c71e..8dd7545b9097 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -434,6 +434,21 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, if (!cfg80211_supported_cipher_suite(&rdev->wiphy, params->cipher)) return -EINVAL; + if (params->ltf_keyseed) { + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SECURE_LTF) || + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SET_KEY_LTF_SEED)) + return -EOPNOTSUPP; + + /* + * LTF key seed is pairwise key material and must only be + * used with a pairwise key + */ + if (!pairwise) + return -EINVAL; + } + return 0; } -- cgit v1.3-14-g43fede From ca283942e5b91894d3a9228eaf789837f66c986f Mon Sep 17 00:00:00 2001 From: "Mike Marciniszyn (Meta)" Date: Thu, 30 Apr 2026 11:08:00 -0400 Subject: net: mdio: Add support for RSFEC Control register for PMA Add the constants associated with RS-FEC configuration and status as well as the indicated separated bits for DEVS1 to convey a separated PMA. Reviewed-by: Andrew Lunn Signed-off-by: Mike Marciniszyn (Meta) Link: https://patch.msgid.link/20260430150802.3521-2-mike.marciniszyn@gmail.com Signed-off-by: Paolo Abeni --- include/uapi/linux/mdio.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 8d769f100de6..b2541c948fc1 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -23,6 +23,10 @@ #define MDIO_MMD_DTEXS 5 /* DTE Extender Sublayer */ #define MDIO_MMD_TC 6 /* Transmission Convergence */ #define MDIO_MMD_AN 7 /* Auto-Negotiation */ +#define MDIO_MMD_SEP_PMA1 8 /* Separated PMA (1) */ +#define MDIO_MMD_SEP_PMA2 9 /* Separated PMA (2) */ +#define MDIO_MMD_SEP_PMA3 10 /* Separated PMA (3) */ +#define MDIO_MMD_SEP_PMA4 11 /* Separated PMA (4) */ #define MDIO_MMD_POWER_UNIT 13 /* PHY Power Unit */ #define MDIO_MMD_C22EXT 29 /* Clause 22 extension */ #define MDIO_MMD_VEND1 30 /* Vendor specific 1 */ @@ -63,6 +67,8 @@ * Lanes B-D are numbered 134-136. */ #define MDIO_PMA_10GBR_FSRT_CSR 147 /* 10GBASE-R fast retrain status and control */ #define MDIO_PMA_10GBR_FECABLE 170 /* 10GBASE-R FEC ability */ +#define MDIO_PMA_RSFEC_CTRL 200 /* RSFEC control */ +#define MDIO_PMA_RSFEC_LANE_MAP 206 /* RSFEC lane mapping */ #define MDIO_PCS_10GBX_STAT1 24 /* 10GBASE-X PCS status 1 */ #define MDIO_PCS_10GBRT_STAT1 32 /* 10GBASE-R/-T PCS status 1 */ #define MDIO_PCS_10GBRT_STAT2 33 /* 10GBASE-R/-T PCS status 2 */ @@ -175,6 +181,10 @@ #define MDIO_DEVS_DTEXS MDIO_DEVS_PRESENT(MDIO_MMD_DTEXS) #define MDIO_DEVS_TC MDIO_DEVS_PRESENT(MDIO_MMD_TC) #define MDIO_DEVS_AN MDIO_DEVS_PRESENT(MDIO_MMD_AN) +#define MDIO_DEVS_SEP_PMA1 MDIO_DEVS_PRESENT(MDIO_MMD_SEP_PMA1) +#define MDIO_DEVS_SEP_PMA2 MDIO_DEVS_PRESENT(MDIO_MMD_SEP_PMA2) +#define MDIO_DEVS_SEP_PMA3 MDIO_DEVS_PRESENT(MDIO_MMD_SEP_PMA3) +#define MDIO_DEVS_SEP_PMA4 MDIO_DEVS_PRESENT(MDIO_MMD_SEP_PMA4) #define MDIO_DEVS_C22EXT MDIO_DEVS_PRESENT(MDIO_MMD_C22EXT) #define MDIO_DEVS_VEND1 MDIO_DEVS_PRESENT(MDIO_MMD_VEND1) #define MDIO_DEVS_VEND2 MDIO_DEVS_PRESENT(MDIO_MMD_VEND2) -- cgit v1.3-14-g43fede From fb19b4d67d81fb91d3c0dce0ddea7fc393a37b2e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 28 Apr 2026 11:06:59 +0200 Subject: wifi: cfg80211: allow devices to advertise extended MLD capa/ops For UHR, multi-link power-management capability lives there, and so it's needed that hostapd knows what to advertise, and clients should have it shown to userspace for information. Repurpose the existing NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS by renaming it to NL80211_ATTR_EXT_MLD_CAPA_AND_OPS (with a define for compatibility) and advertise the capabilities. We can also later use the value, if needed, to set per-station capabilities on STAs added to AP interfaces. Link: https://patch.msgid.link/20260428110915.e808e70feed6.I378a7c017bfc1ebb072fa8d5d1db2ac9b45596c9@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 15 +++++++++------ net/wireless/nl80211.c | 18 ++++++++++++------ 3 files changed, 23 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 13e035fecf7f..5755aa288912 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5969,6 +5969,7 @@ struct wiphy_vendor_command { * @extended_capabilities_len: length of the extended capabilities * @eml_capabilities: EML capabilities (for MLO) * @mld_capa_and_ops: MLD capabilities and operations (for MLO) + * @ext_mld_capa_and_ops: Extended MLD capabilities and operations (for MLO) */ struct wiphy_iftype_ext_capab { enum nl80211_iftype iftype; @@ -5977,6 +5978,7 @@ struct wiphy_iftype_ext_capab { u8 extended_capabilities_len; u16 eml_capabilities; u16 mld_capa_and_ops; + u16 ext_mld_capa_and_ops; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6c7e6c05b9a8..235d7ae72e60 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3004,11 +3004,13 @@ enum nl80211_commands { * @NL80211_ATTR_EPCS: Flag attribute indicating that EPCS is enabled for a * station interface. * - * @NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS: Extended MLD capabilities and - * operations that userspace implements to use during association/ML - * link reconfig, currently only "BTM MLD Recommendation For Multiple - * APs Support". Drivers may set additional flags that they support - * in the kernel or device. + * @NL80211_ATTR_EXT_MLD_CAPA_AND_OPS: Extended MLD capabilities and operations. + * For association and link reconfiguration, indicates extra capabilities + * that userspace implements, currently only "BTM MLD Recommendation For + * Multiple APs Support". + * For wiphy information, additional flags that drivers will set, but + * this is informational only for userspace (it's not expected to set + * these.) * * @NL80211_ATTR_WIPHY_RADIO_INDEX: (int) Integer attribute denoting the index * of the radio in interest. Internally a value of -1 is used to @@ -3715,7 +3717,7 @@ enum nl80211_attrs { NL80211_ATTR_MLO_RECONF_REM_LINKS, NL80211_ATTR_EPCS, - NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS, + NL80211_ATTR_EXT_MLD_CAPA_AND_OPS, NL80211_ATTR_WIPHY_RADIO_INDEX, @@ -3769,6 +3771,7 @@ enum nl80211_attrs { #define NL80211_ATTR_SAE_DATA NL80211_ATTR_AUTH_DATA #define NL80211_ATTR_CSA_C_OFF_BEACON NL80211_ATTR_CNTDWN_OFFS_BEACON #define NL80211_ATTR_CSA_C_OFF_PRESP NL80211_ATTR_CNTDWN_OFFS_PRESP +#define NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS NL80211_ATTR_EXT_MLD_CAPA_AND_OPS /* * Allow user space programs to use #ifdef on new attributes by defining them diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 61b1716daf1e..f935b18112e8 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1061,7 +1061,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NL80211_MAX_SUPP_SELECTORS), [NL80211_ATTR_MLO_RECONF_REM_LINKS] = { .type = NLA_U16 }, [NL80211_ATTR_EPCS] = { .type = NLA_FLAG }, - [NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS] = { .type = NLA_U16 }, + [NL80211_ATTR_EXT_MLD_CAPA_AND_OPS] = { .type = NLA_U16 }, [NL80211_ATTR_WIPHY_RADIO_INDEX] = { .type = NLA_U8 }, [NL80211_ATTR_S1G_LONG_BEACON_PERIOD] = NLA_POLICY_MIN(NLA_U8, 2), [NL80211_ATTR_S1G_SHORT_BEACON] = @@ -3596,6 +3596,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, NL80211_ATTR_MLD_CAPA_AND_OPS, capab->mld_capa_and_ops))) goto nla_put_failure; + if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_MLO && + capab->ext_mld_capa_and_ops && + nla_put_u16(msg, + NL80211_ATTR_EXT_MLD_CAPA_AND_OPS, + capab->ext_mld_capa_and_ops)) + goto nla_put_failure; nla_nest_end(msg, nested_ext_capab); if (state->split) @@ -13059,9 +13065,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } - if (info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]) + if (info->attrs[NL80211_ATTR_EXT_MLD_CAPA_AND_OPS]) req.ext_mld_capa_ops = - nla_get_u16(info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]); + nla_get_u16(info->attrs[NL80211_ATTR_EXT_MLD_CAPA_AND_OPS]); } else { if (req.link_id >= 0) return -EINVAL; @@ -13072,7 +13078,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) return PTR_ERR(req.bss); ap_addr = req.bss->bssid; - if (info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]) + if (info->attrs[NL80211_ATTR_EXT_MLD_CAPA_AND_OPS]) return -EINVAL; } @@ -19000,9 +19006,9 @@ static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info) goto out; } - if (info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]) + if (info->attrs[NL80211_ATTR_EXT_MLD_CAPA_AND_OPS]) req.ext_mld_capa_ops = - nla_get_u16(info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]); + nla_get_u16(info->attrs[NL80211_ATTR_EXT_MLD_CAPA_AND_OPS]); err = cfg80211_assoc_ml_reconf(rdev, dev, &req); -- cgit v1.3-14-g43fede From 1cf1d06e956dfbb05a7f69f64ab3c8938117eabe Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 28 Apr 2026 11:25:32 +0200 Subject: wifi: cfg80211: allow representing NPCA in chandef Add the necessary fields to the chandef data structure to represent NPCA (the NPCA primary channel and NPCA punctured/disabled subchannels bitmap), and the code to check these for validity, compatibility, as well as allowing it to be passed for AP mode for capable devices. Compatibility is assumed to only be the case when it's actually identical, enabling later management of this in channel contexts in mac80211 for multiple APs, but requiring userspace to set up the identical chandef on all AP interfaces that share a channel (and BSS color.) Link: https://patch.msgid.link/20260428112708.46f3872aeb35.I85888dab88a6659ba52db4b3318979ca5bcfc0c8@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 11 +++- include/uapi/linux/nl80211.h | 6 +++ net/wireless/chan.c | 59 ++++++++++++++++++--- net/wireless/nl80211.c | 120 +++++++++++++++++++++++++++++++++++++------ net/wireless/nl80211.h | 5 +- net/wireless/pmsr.c | 2 +- net/wireless/trace.h | 16 ++++-- 7 files changed, 189 insertions(+), 30 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5755aa288912..16e11c5718b5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -848,6 +848,7 @@ struct key_params { /** * struct cfg80211_chan_def - channel definition * @chan: the (control) channel + * @npca_chan: the NPCA primary channel * @width: channel width * @center_freq1: center frequency of first segment * @center_freq2: center frequency of second segment @@ -860,18 +861,22 @@ struct key_params { * @punctured: mask of the punctured 20 MHz subchannels, with * bits turned on being disabled (punctured); numbered * from lower to higher frequency (like in the spec) + * @npca_punctured: NPCA puncturing bitmap, like @punctured but for + * NPCA transmissions. If NPCA is used (@npca_chan is not %NULL) + * this will be a superset of the @punctured bimap. * @s1g_primary_2mhz: Indicates if the control channel pointed to * by 'chan' exists as a 1MHz primary subchannel within an * S1G 2MHz primary channel. */ struct cfg80211_chan_def { struct ieee80211_channel *chan; + struct ieee80211_channel *npca_chan; enum nl80211_chan_width width; u32 center_freq1; u32 center_freq2; struct ieee80211_edmg edmg; u16 freq1_offset; - u16 punctured; + u16 punctured, npca_punctured; bool s1g_primary_2mhz; }; @@ -1018,7 +1023,9 @@ cfg80211_chandef_identical(const struct cfg80211_chan_def *chandef1, chandef1->freq1_offset == chandef2->freq1_offset && chandef1->center_freq2 == chandef2->center_freq2 && chandef1->punctured == chandef2->punctured && - chandef1->s1g_primary_2mhz == chandef2->s1g_primary_2mhz); + chandef1->s1g_primary_2mhz == chandef2->s1g_primary_2mhz && + chandef1->npca_chan == chandef2->npca_chan && + chandef1->npca_punctured == chandef2->npca_punctured); } /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 235d7ae72e60..9998f6c0a665 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3162,6 +3162,9 @@ enum nl80211_commands { * encrypted over the air. Enhanced Privacy Protection (EPP), as defined * in IEEE P802.11bi/D4.0, mandates this encryption. * + * @NL80211_ATTR_NPCA_PRIMARY_FREQ: NPCA primary channel (u32) + * @NL80211_ATTR_NPCA_PUNCT_BITMAP: NPCA puncturing bitmap (u32) + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3757,6 +3760,9 @@ enum nl80211_attrs { NL80211_ATTR_ASSOC_ENCRYPTED, + NL80211_ATTR_NPCA_PRIMARY_FREQ, + NL80211_ATTR_NPCA_PUNCT_BITMAP, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 8954ac1659c1..38b83b44b5dc 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -138,9 +138,10 @@ static const struct cfg80211_per_bw_puncturing_values per_bw_puncturing[] = { CFG80211_PER_BW_VALID_PUNCTURING_VALUES(320) }; -static bool valid_puncturing_bitmap(const struct cfg80211_chan_def *chandef) +static bool valid_puncturing_bitmap(const struct cfg80211_chan_def *chandef, + u32 primary_center, u32 punctured) { - u32 idx, i, start_freq, primary_center = chandef->chan->center_freq; + u32 idx, i, start_freq; switch (chandef->width) { case NL80211_CHAN_WIDTH_80: @@ -156,18 +157,18 @@ static bool valid_puncturing_bitmap(const struct cfg80211_chan_def *chandef) start_freq = chandef->center_freq1 - 160; break; default: - return chandef->punctured == 0; + return punctured == 0; } - if (!chandef->punctured) + if (!punctured) return true; /* check if primary channel is punctured */ - if (chandef->punctured & (u16)BIT((primary_center - start_freq) / 20)) + if (punctured & (u16)BIT((primary_center - start_freq) / 20)) return false; for (i = 0; i < per_bw_puncturing[idx].len; i++) { - if (per_bw_puncturing[idx].valid_values[i] == chandef->punctured) + if (per_bw_puncturing[idx].valid_values[i] == punctured) return true; } @@ -458,6 +459,40 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) if (!cfg80211_chandef_valid_control_freq(chandef, control_freq)) return false; + if (chandef->npca_chan) { + bool pri_upper, npca_upper; + u32 cf1; + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_320: + break; + default: + return false; + } + + if (!cfg80211_chandef_valid_control_freq(chandef, + chandef->npca_chan->center_freq)) + return false; + + cf1 = chandef->center_freq1; + pri_upper = chandef->chan->center_freq > cf1; + npca_upper = chandef->npca_chan->center_freq > cf1; + + if (pri_upper == npca_upper) + return false; + + if (!valid_puncturing_bitmap(chandef, + chandef->npca_chan->center_freq, + chandef->npca_punctured) || + (chandef->punctured & chandef->npca_punctured) != + chandef->punctured) + return false; + } else if (chandef->npca_punctured) { + return false; + } + if (!cfg80211_valid_center_freq(chandef->center_freq1, chandef->width)) return false; @@ -477,7 +512,8 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) if (!cfg80211_chandef_is_s1g(chandef) && chandef->s1g_primary_2mhz) return false; - return valid_puncturing_bitmap(chandef); + return valid_puncturing_bitmap(chandef, control_freq, + chandef->punctured); } EXPORT_SYMBOL(cfg80211_chandef_valid); @@ -564,6 +600,15 @@ _cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, if (c1->width == c2->width) return NULL; + /* + * We need NPCA to be compatible for some scenarios such as + * multiple APs, but in this case userspace should configure + * identical chandefs including NPCA, even if perhaps one of + * the AP interfaces doesn't even advertise it. + */ + if (c1->npca_chan || c2->npca_chan) + return NULL; + /* * can't be compatible if one of them is 5/10 MHz or S1G * but they don't have the same width. diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f935b18112e8..cd72f187a606 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1090,6 +1090,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_NAN_MAX_CHAN_SWITCH_TIME] = { .type = NLA_U16 }, [NL80211_ATTR_NAN_PEER_MAPS] = NLA_POLICY_NESTED_ARRAY(nl80211_nan_peer_map_policy), + [NL80211_ATTR_NPCA_PRIMARY_FREQ] = { .type = NLA_U32 }, + [NL80211_ATTR_NPCA_PUNCT_BITMAP] = + NLA_POLICY_FULL_RANGE(NLA_U32, &nl80211_punct_bitmap_range), }; /* policy for the key attributes */ @@ -3913,7 +3916,8 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) static int _nl80211_parse_chandef(struct cfg80211_registered_device *rdev, struct netlink_ext_ack *extack, struct nlattr **attrs, bool monitor, - struct cfg80211_chan_def *chandef) + struct cfg80211_chan_def *chandef, + bool permit_npca) { u32 control_freq; @@ -4027,6 +4031,34 @@ static int _nl80211_parse_chandef(struct cfg80211_registered_device *rdev, } } + if (attrs[NL80211_ATTR_NPCA_PRIMARY_FREQ]) { + if (!permit_npca) { + NL_SET_ERR_MSG_ATTR(extack, + attrs[NL80211_ATTR_NPCA_PRIMARY_FREQ], + "NPCA not supported"); + return -EINVAL; + } + + chandef->npca_chan = + ieee80211_get_channel(&rdev->wiphy, + nla_get_u32(attrs[NL80211_ATTR_NPCA_PRIMARY_FREQ])); + if (!chandef->npca_chan) { + NL_SET_ERR_MSG_ATTR(extack, + attrs[NL80211_ATTR_NPCA_PRIMARY_FREQ], + "invalid NPCA primary channel"); + return -EINVAL; + } + + chandef->npca_punctured = + nla_get_u32_default(attrs[NL80211_ATTR_NPCA_PUNCT_BITMAP], + chandef->punctured); + } else if (attrs[NL80211_ATTR_NPCA_PUNCT_BITMAP]) { + NL_SET_ERR_MSG_ATTR(extack, + attrs[NL80211_ATTR_NPCA_PUNCT_BITMAP], + "NPCA puncturing only valid with NPCA"); + return -EINVAL; + } + if (!cfg80211_chandef_valid(chandef)) { NL_SET_ERR_MSG_ATTR(extack, attrs[NL80211_ATTR_WIPHY_FREQ], "invalid channel definition"); @@ -4054,9 +4086,11 @@ static int _nl80211_parse_chandef(struct cfg80211_registered_device *rdev, int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, struct netlink_ext_ack *extack, struct nlattr **attrs, - struct cfg80211_chan_def *chandef) + struct cfg80211_chan_def *chandef, + bool permit_npca) { - return _nl80211_parse_chandef(rdev, extack, attrs, false, chandef); + return _nl80211_parse_chandef(rdev, extack, attrs, false, chandef, + permit_npca); } static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, @@ -4069,6 +4103,7 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype = NL80211_IFTYPE_MONITOR; struct wireless_dev *wdev = NULL; int link_id = _link_id; + bool permit_npca; if (dev) wdev = dev->ieee80211_ptr; @@ -4083,9 +4118,13 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, link_id = 0; } + /* allow parsing it - will check on start_ap or below */ + permit_npca = iftype == NL80211_IFTYPE_AP || + iftype == NL80211_IFTYPE_P2P_GO; + result = _nl80211_parse_chandef(rdev, info->extack, info->attrs, iftype == NL80211_IFTYPE_MONITOR, - &chandef); + &chandef, permit_npca); if (result) return result; @@ -4104,6 +4143,9 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, return -EBUSY; /* Only allow dynamic channel width changes */ + cur_chan = wdev->links[link_id].ap.chandef.npca_chan; + if (chandef.npca_chan != cur_chan) + return -EBUSY; cur_chan = wdev->links[link_id].ap.chandef.chan; if (chandef.chan != cur_chan) return -EBUSY; @@ -4588,6 +4630,15 @@ int nl80211_send_chandef(struct sk_buff *msg, const struct cfg80211_chan_def *ch nla_put_flag(msg, NL80211_ATTR_S1G_PRIMARY_2MHZ)) return -ENOBUFS; + if (chandef->npca_chan && + nla_put_u32(msg, NL80211_ATTR_NPCA_PRIMARY_FREQ, + chandef->npca_chan->center_freq)) + return -ENOBUFS; + if (chandef->npca_punctured && + nla_put_u32(msg, NL80211_ATTR_NPCA_PUNCT_BITMAP, + chandef->npca_punctured)) + return -ENOBUFS; + return 0; } EXPORT_SYMBOL(nl80211_send_chandef); @@ -7092,6 +7143,28 @@ nl80211_parse_s1g_short_beacon(struct cfg80211_registered_device *rdev, return 0; } +static int nl80211_check_npca(struct cfg80211_registered_device *rdev, + const struct cfg80211_chan_def *chandef, + enum nl80211_iftype iftype, + struct netlink_ext_ack *extack) +{ + const struct ieee80211_supported_band *sband; + const struct ieee80211_sta_uhr_cap *uhr_cap; + + if (!chandef->npca_chan) + return 0; + + sband = rdev->wiphy.bands[chandef->chan->band]; + uhr_cap = ieee80211_get_uhr_iftype_cap(sband, iftype); + + if (uhr_cap && + (uhr_cap->mac.mac_cap[0] & IEEE80211_UHR_MAC_CAP0_NPCA_SUPP)) + return 0; + + NL_SET_ERR_MSG(extack, "NPCA not supported"); + return -EINVAL; +} + static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -7231,7 +7304,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { err = nl80211_parse_chandef(rdev, info->extack, info->attrs, - ¶ms->chandef); + ¶ms->chandef, true); if (err) goto out; } else if (wdev->valid_links) { @@ -7250,6 +7323,11 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (err) goto out; + err = nl80211_check_npca(rdev, ¶ms->chandef, wdev->iftype, + info->extack); + if (err) + goto out; + beacon_check.iftype = wdev->iftype; beacon_check.relax = true; beacon_check.reg_power = @@ -11801,7 +11879,8 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, if (dfs_region == NL80211_DFS_UNSET) return -EINVAL; - err = nl80211_parse_chandef(rdev, info->extack, info->attrs, &chandef); + err = nl80211_parse_chandef(rdev, info->extack, info->attrs, &chandef, + false); if (err) return err; @@ -11890,7 +11969,8 @@ static int nl80211_notify_radar_detection(struct sk_buff *skb, return -EINVAL; } - err = nl80211_parse_chandef(rdev, info->extack, info->attrs, &chandef); + err = nl80211_parse_chandef(rdev, info->extack, info->attrs, &chandef, + false); if (err) { GENL_SET_ERR_MSG(info, "Unable to extract chandef info"); return err; @@ -11973,6 +12053,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) int err; bool need_new_beacon = false; bool need_handle_dfs_flag = true; + bool permit_npca = false; u32 cs_count; if (!rdev->ops->channel_switch || @@ -11990,6 +12071,8 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) */ need_handle_dfs_flag = false; + permit_npca = true; + /* useless if AP is not running */ if (!wdev->links[link_id].ap.beacon_interval) return -ENOTCONN; @@ -12027,7 +12110,12 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) params.count = cs_count; err = nl80211_parse_chandef(rdev, info->extack, info->attrs, - ¶ms.chandef); + ¶ms.chandef, permit_npca); + if (err) + goto free; + + err = nl80211_check_npca(rdev, ¶ms.chandef, wdev->iftype, + info->extack); if (err) goto free; @@ -13301,7 +13389,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) } err = nl80211_parse_chandef(rdev, info->extack, info->attrs, - &ibss.chandef); + &ibss.chandef, false); if (err) return err; @@ -14310,7 +14398,8 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, duration > rdev->wiphy.max_remain_on_channel_duration) return -EINVAL; - err = nl80211_parse_chandef(rdev, info->extack, info->attrs, &chandef); + err = nl80211_parse_chandef(rdev, info->extack, info->attrs, &chandef, + false); if (err) return err; @@ -14539,7 +14628,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) chandef.chan = NULL; if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { err = nl80211_parse_chandef(rdev, info->extack, info->attrs, - &chandef); + &chandef, false); if (err) return err; } @@ -14947,7 +15036,7 @@ static int nl80211_join_ocb(struct sk_buff *skb, struct genl_info *info) int err; err = nl80211_parse_chandef(rdev, info->extack, info->attrs, - &setup.chandef); + &setup.chandef, false); if (err) return err; @@ -15023,7 +15112,7 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { err = nl80211_parse_chandef(rdev, info->extack, info->attrs, - &setup.chandef); + &setup.chandef, false); if (err) return err; } else { @@ -17027,7 +17116,7 @@ static int nl80211_parse_nan_channel(struct cfg80211_registered_device *rdev, return ret; ret = nl80211_parse_chandef(rdev, info->extack, channel_parsed, - &chandef); + &chandef, false); if (ret) return ret; @@ -18026,7 +18115,8 @@ static int nl80211_tdls_channel_switch(struct sk_buff *skb, !info->attrs[NL80211_ATTR_OPER_CLASS]) return -EINVAL; - err = nl80211_parse_chandef(rdev, info->extack, info->attrs, &chandef); + err = nl80211_parse_chandef(rdev, info->extack, info->attrs, &chandef, + false); if (err) return err; diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 048ba92c3e42..bdb065d14054 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file - * Copyright (C) 2018, 2020-2025 Intel Corporation + * Copyright (C) 2018, 2020-2026 Intel Corporation */ #ifndef __NET_WIRELESS_NL80211_H #define __NET_WIRELESS_NL80211_H @@ -25,7 +25,8 @@ static inline u64 wdev_id(struct wireless_dev *wdev) int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, struct netlink_ext_ack *extack, struct nlattr **attrs, - struct cfg80211_chan_def *chandef); + struct cfg80211_chan_def *chandef, + bool npca_permitted); int nl80211_parse_random_mac(struct nlattr **attrs, u8 *mac_addr, u8 *mac_addr_mask); diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index f77658b6fccc..e45fc1fb65c2 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -349,7 +349,7 @@ static int pmsr_parse_peer(struct cfg80211_registered_device *rdev, return err; err = nl80211_parse_chandef(rdev, info->extack, info->attrs, - &out->chandef); + &out->chandef, false); if (err) return err; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index a68d356fe127..94944f2a39a4 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -141,7 +141,9 @@ __field(u32, center_freq1) \ __field(u32, freq1_offset) \ __field(u32, center_freq2) \ - __field(u16, punctured) + __field(u16, punctured) \ + __field(u32, npca_pri_freq) \ + __field(u16, npca_punctured) #define CHAN_DEF_ASSIGN(chandef) \ do { \ if ((chandef) && (chandef)->chan) { \ @@ -155,6 +157,11 @@ __entry->freq1_offset = (chandef)->freq1_offset;\ __entry->center_freq2 = (chandef)->center_freq2;\ __entry->punctured = (chandef)->punctured; \ + __entry->npca_pri_freq = \ + (chandef)->npca_chan ? \ + (chandef)->npca_chan->center_freq : 0; \ + __entry->npca_punctured = \ + (chandef)->npca_punctured; \ } else { \ __entry->band = 0; \ __entry->control_freq = 0; \ @@ -164,14 +171,17 @@ __entry->freq1_offset = 0; \ __entry->center_freq2 = 0; \ __entry->punctured = 0; \ + __entry->npca_pri_freq = 0; \ + __entry->npca_punctured = 0; \ } \ } while (0) #define CHAN_DEF_PR_FMT \ - "band: %d, control freq: %u.%03u, width: %d, cf1: %u.%03u, cf2: %u, punct: 0x%x" + "band: %d, control freq: %u.%03u, width: %d, cf1: %u.%03u, cf2: %u, punct: 0x%x, npca:%u, npca_punct:0x%x" #define CHAN_DEF_PR_ARG __entry->band, __entry->control_freq, \ __entry->freq_offset, __entry->width, \ __entry->center_freq1, __entry->freq1_offset, \ - __entry->center_freq2, __entry->punctured + __entry->center_freq2, __entry->punctured, \ + __entry->npca_pri_freq, __entry->npca_punctured #define FILS_AAD_ASSIGN(fa) \ do { \ -- cgit v1.3-14-g43fede From a54f499838292c1768f6575ed1ec7cf35f1b6489 Mon Sep 17 00:00:00 2001 From: Christoph Böhmwalder Date: Wed, 6 May 2026 14:45:40 +0200 Subject: drbd: move UAPI headers to include/uapi/linux/ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit drbd.h and drbd_limits.h contain only type definitions, enums, and constants shared between kernel and userspace. These should be part of UAPI. Split the genl_api header into two: the genlmsghdr and the enums are UAPI, the rest stays there for now (it will be removed by one of the next commits in this series). drbd_config.h is clearly DRBD-internal, so move it there. Signed-off-by: Christoph Böhmwalder Acked-by: Jakub Kicinski Link: https://patch.msgid.link/20260506124541.1951772-2-christoph.boehmwalder@linbit.com Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_buildtag.c | 2 +- drivers/block/drbd/drbd_config.h | 16 ++ drivers/block/drbd/drbd_int.h | 2 +- include/linux/drbd.h | 392 --------------------------------- include/linux/drbd_config.h | 16 -- include/linux/drbd_genl_api.h | 40 ---- include/linux/drbd_limits.h | 251 --------------------- include/uapi/linux/drbd.h | 432 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/drbd_limits.h | 251 +++++++++++++++++++++ 9 files changed, 701 insertions(+), 701 deletions(-) create mode 100644 drivers/block/drbd/drbd_config.h delete mode 100644 include/linux/drbd.h delete mode 100644 include/linux/drbd_config.h delete mode 100644 include/linux/drbd_limits.h create mode 100644 include/uapi/linux/drbd.h create mode 100644 include/uapi/linux/drbd_limits.h (limited to 'include/uapi/linux') diff --git a/drivers/block/drbd/drbd_buildtag.c b/drivers/block/drbd/drbd_buildtag.c index cb1aa66d7d5d..cd0389488f63 100644 --- a/drivers/block/drbd/drbd_buildtag.c +++ b/drivers/block/drbd/drbd_buildtag.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -#include +#include "drbd_config.h" #include const char *drbd_buildtag(void) diff --git a/drivers/block/drbd/drbd_config.h b/drivers/block/drbd/drbd_config.h new file mode 100644 index 000000000000..d215365c6bb1 --- /dev/null +++ b/drivers/block/drbd/drbd_config.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * drbd_config.h + * DRBD's compile time configuration. + */ + +#ifndef DRBD_CONFIG_H +#define DRBD_CONFIG_H + +extern const char *drbd_buildtag(void); + +#define REL_VERSION "8.4.11" +#define PRO_VERSION_MIN 86 +#define PRO_VERSION_MAX 101 + +#endif diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index f6d6276974ee..f3d746a6d6fd 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -34,7 +34,7 @@ #include #include #include -#include +#include "drbd_config.h" #include "drbd_strings.h" #include "drbd_state.h" #include "drbd_protocol.h" diff --git a/include/linux/drbd.h b/include/linux/drbd.h deleted file mode 100644 index 5468a2399d48..000000000000 --- a/include/linux/drbd.h +++ /dev/null @@ -1,392 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - drbd.h - Kernel module for 2.6.x Kernels - - This file is part of DRBD by Philipp Reisner and Lars Ellenberg. - - Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. - Copyright (C) 2001-2008, Philipp Reisner . - Copyright (C) 2001-2008, Lars Ellenberg . - - -*/ -#ifndef DRBD_H -#define DRBD_H -#include - -#ifdef __KERNEL__ -#include -#include -#else -#include -#include -#include - -/* Although the Linux source code makes a difference between - generic endianness and the bitfields' endianness, there is no - architecture as of Linux-2.6.24-rc4 where the bitfields' endianness - does not match the generic endianness. */ - -#if __BYTE_ORDER == __LITTLE_ENDIAN -#define __LITTLE_ENDIAN_BITFIELD -#elif __BYTE_ORDER == __BIG_ENDIAN -#define __BIG_ENDIAN_BITFIELD -#else -# error "sorry, weird endianness on this box" -#endif - -#endif - -enum drbd_io_error_p { - EP_PASS_ON, /* FIXME should the better be named "Ignore"? */ - EP_CALL_HELPER, - EP_DETACH -}; - -enum drbd_fencing_p { - FP_NOT_AVAIL = -1, /* Not a policy */ - FP_DONT_CARE = 0, - FP_RESOURCE, - FP_STONITH -}; - -enum drbd_disconnect_p { - DP_RECONNECT, - DP_DROP_NET_CONF, - DP_FREEZE_IO -}; - -enum drbd_after_sb_p { - ASB_DISCONNECT, - ASB_DISCARD_YOUNGER_PRI, - ASB_DISCARD_OLDER_PRI, - ASB_DISCARD_ZERO_CHG, - ASB_DISCARD_LEAST_CHG, - ASB_DISCARD_LOCAL, - ASB_DISCARD_REMOTE, - ASB_CONSENSUS, - ASB_DISCARD_SECONDARY, - ASB_CALL_HELPER, - ASB_VIOLENTLY -}; - -enum drbd_on_no_data { - OND_IO_ERROR, - OND_SUSPEND_IO -}; - -enum drbd_on_congestion { - OC_BLOCK, - OC_PULL_AHEAD, - OC_DISCONNECT, -}; - -enum drbd_read_balancing { - RB_PREFER_LOCAL, - RB_PREFER_REMOTE, - RB_ROUND_ROBIN, - RB_LEAST_PENDING, - RB_CONGESTED_REMOTE, - RB_32K_STRIPING, - RB_64K_STRIPING, - RB_128K_STRIPING, - RB_256K_STRIPING, - RB_512K_STRIPING, - RB_1M_STRIPING, -}; - -/* KEEP the order, do not delete or insert. Only append. */ -enum drbd_ret_code { - ERR_CODE_BASE = 100, - NO_ERROR = 101, - ERR_LOCAL_ADDR = 102, - ERR_PEER_ADDR = 103, - ERR_OPEN_DISK = 104, - ERR_OPEN_MD_DISK = 105, - ERR_DISK_NOT_BDEV = 107, - ERR_MD_NOT_BDEV = 108, - ERR_DISK_TOO_SMALL = 111, - ERR_MD_DISK_TOO_SMALL = 112, - ERR_BDCLAIM_DISK = 114, - ERR_BDCLAIM_MD_DISK = 115, - ERR_MD_IDX_INVALID = 116, - ERR_IO_MD_DISK = 118, - ERR_MD_INVALID = 119, - ERR_AUTH_ALG = 120, - ERR_AUTH_ALG_ND = 121, - ERR_NOMEM = 122, - ERR_DISCARD_IMPOSSIBLE = 123, - ERR_DISK_CONFIGURED = 124, - ERR_NET_CONFIGURED = 125, - ERR_MANDATORY_TAG = 126, - ERR_MINOR_INVALID = 127, - ERR_INTR = 129, /* EINTR */ - ERR_RESIZE_RESYNC = 130, - ERR_NO_PRIMARY = 131, - ERR_RESYNC_AFTER = 132, - ERR_RESYNC_AFTER_CYCLE = 133, - ERR_PAUSE_IS_SET = 134, - ERR_PAUSE_IS_CLEAR = 135, - ERR_PACKET_NR = 137, - ERR_NO_DISK = 138, - ERR_NOT_PROTO_C = 139, - ERR_NOMEM_BITMAP = 140, - ERR_INTEGRITY_ALG = 141, /* DRBD 8.2 only */ - ERR_INTEGRITY_ALG_ND = 142, /* DRBD 8.2 only */ - ERR_CPU_MASK_PARSE = 143, /* DRBD 8.2 only */ - ERR_CSUMS_ALG = 144, /* DRBD 8.2 only */ - ERR_CSUMS_ALG_ND = 145, /* DRBD 8.2 only */ - ERR_VERIFY_ALG = 146, /* DRBD 8.2 only */ - ERR_VERIFY_ALG_ND = 147, /* DRBD 8.2 only */ - ERR_CSUMS_RESYNC_RUNNING= 148, /* DRBD 8.2 only */ - ERR_VERIFY_RUNNING = 149, /* DRBD 8.2 only */ - ERR_DATA_NOT_CURRENT = 150, - ERR_CONNECTED = 151, /* DRBD 8.3 only */ - ERR_PERM = 152, - ERR_NEED_APV_93 = 153, - ERR_STONITH_AND_PROT_A = 154, - ERR_CONG_NOT_PROTO_A = 155, - ERR_PIC_AFTER_DEP = 156, - ERR_PIC_PEER_DEP = 157, - ERR_RES_NOT_KNOWN = 158, - ERR_RES_IN_USE = 159, - ERR_MINOR_CONFIGURED = 160, - ERR_MINOR_OR_VOLUME_EXISTS = 161, - ERR_INVALID_REQUEST = 162, - ERR_NEED_APV_100 = 163, - ERR_NEED_ALLOW_TWO_PRI = 164, - ERR_MD_UNCLEAN = 165, - ERR_MD_LAYOUT_CONNECTED = 166, - ERR_MD_LAYOUT_TOO_BIG = 167, - ERR_MD_LAYOUT_TOO_SMALL = 168, - ERR_MD_LAYOUT_NO_FIT = 169, - ERR_IMPLICIT_SHRINK = 170, - /* insert new ones above this line */ - AFTER_LAST_ERR_CODE -}; - -#define DRBD_PROT_A 1 -#define DRBD_PROT_B 2 -#define DRBD_PROT_C 3 - -enum drbd_role { - R_UNKNOWN = 0, - R_PRIMARY = 1, /* role */ - R_SECONDARY = 2, /* role */ - R_MASK = 3, -}; - -/* The order of these constants is important. - * The lower ones (=C_WF_REPORT_PARAMS ==> There is a socket - */ -enum drbd_conns { - C_STANDALONE, - C_DISCONNECTING, /* Temporal state on the way to StandAlone. */ - C_UNCONNECTED, /* >= C_UNCONNECTED -> inc_net() succeeds */ - - /* These temporal states are all used on the way - * from >= C_CONNECTED to Unconnected. - * The 'disconnect reason' states - * I do not allow to change between them. */ - C_TIMEOUT, - C_BROKEN_PIPE, - C_NETWORK_FAILURE, - C_PROTOCOL_ERROR, - C_TEAR_DOWN, - - C_WF_CONNECTION, - C_WF_REPORT_PARAMS, /* we have a socket */ - C_CONNECTED, /* we have introduced each other */ - C_STARTING_SYNC_S, /* starting full sync by admin request. */ - C_STARTING_SYNC_T, /* starting full sync by admin request. */ - C_WF_BITMAP_S, - C_WF_BITMAP_T, - C_WF_SYNC_UUID, - - /* All SyncStates are tested with this comparison - * xx >= C_SYNC_SOURCE && xx <= C_PAUSED_SYNC_T */ - C_SYNC_SOURCE, - C_SYNC_TARGET, - C_VERIFY_S, - C_VERIFY_T, - C_PAUSED_SYNC_S, - C_PAUSED_SYNC_T, - - C_AHEAD, - C_BEHIND, - - C_MASK = 31 -}; - -enum drbd_disk_state { - D_DISKLESS, - D_ATTACHING, /* In the process of reading the meta-data */ - D_FAILED, /* Becomes D_DISKLESS as soon as we told it the peer */ - /* when >= D_FAILED it is legal to access mdev->ldev */ - D_NEGOTIATING, /* Late attaching state, we need to talk to the peer */ - D_INCONSISTENT, - D_OUTDATED, - D_UNKNOWN, /* Only used for the peer, never for myself */ - D_CONSISTENT, /* Might be D_OUTDATED, might be D_UP_TO_DATE ... */ - D_UP_TO_DATE, /* Only this disk state allows applications' IO ! */ - D_MASK = 15 -}; - -union drbd_state { -/* According to gcc's docs is the ... - * The order of allocation of bit-fields within a unit (C90 6.5.2.1, C99 6.7.2.1). - * Determined by ABI. - * pointed out by Maxim Uvarov q - * even though we transmit as "cpu_to_be32(state)", - * the offsets of the bitfields still need to be swapped - * on different endianness. - */ - struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) - unsigned role:2 ; /* 3/4 primary/secondary/unknown */ - unsigned peer:2 ; /* 3/4 primary/secondary/unknown */ - unsigned conn:5 ; /* 17/32 cstates */ - unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ - unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ - unsigned susp:1 ; /* 2/2 IO suspended no/yes (by user) */ - unsigned aftr_isp:1 ; /* isp .. imposed sync pause */ - unsigned peer_isp:1 ; - unsigned user_isp:1 ; - unsigned susp_nod:1 ; /* IO suspended because no data */ - unsigned susp_fen:1 ; /* IO suspended because fence peer handler runs*/ - unsigned _pad:9; /* 0 unused */ -#elif defined(__BIG_ENDIAN_BITFIELD) - unsigned _pad:9; - unsigned susp_fen:1 ; - unsigned susp_nod:1 ; - unsigned user_isp:1 ; - unsigned peer_isp:1 ; - unsigned aftr_isp:1 ; /* isp .. imposed sync pause */ - unsigned susp:1 ; /* 2/2 IO suspended no/yes */ - unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ - unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ - unsigned conn:5 ; /* 17/32 cstates */ - unsigned peer:2 ; /* 3/4 primary/secondary/unknown */ - unsigned role:2 ; /* 3/4 primary/secondary/unknown */ -#else -# error "this endianness is not supported" -#endif - }; - unsigned int i; -}; - -enum drbd_state_rv { - SS_CW_NO_NEED = 4, - SS_CW_SUCCESS = 3, - SS_NOTHING_TO_DO = 2, - SS_SUCCESS = 1, - SS_UNKNOWN_ERROR = 0, /* Used to sleep longer in _drbd_request_state */ - SS_TWO_PRIMARIES = -1, - SS_NO_UP_TO_DATE_DISK = -2, - SS_NO_LOCAL_DISK = -4, - SS_NO_REMOTE_DISK = -5, - SS_CONNECTED_OUTDATES = -6, - SS_PRIMARY_NOP = -7, - SS_RESYNC_RUNNING = -8, - SS_ALREADY_STANDALONE = -9, - SS_CW_FAILED_BY_PEER = -10, - SS_IS_DISKLESS = -11, - SS_DEVICE_IN_USE = -12, - SS_NO_NET_CONFIG = -13, - SS_NO_VERIFY_ALG = -14, /* drbd-8.2 only */ - SS_NEED_CONNECTION = -15, /* drbd-8.2 only */ - SS_LOWER_THAN_OUTDATED = -16, - SS_NOT_SUPPORTED = -17, /* drbd-8.2 only */ - SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ - SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ - SS_O_VOL_PEER_PRI = -20, - SS_OUTDATE_WO_CONN = -21, - SS_AFTER_LAST_ERROR = -22, /* Keep this at bottom */ -}; - -#define SHARED_SECRET_MAX 64 - -#define MDF_CONSISTENT (1 << 0) -#define MDF_PRIMARY_IND (1 << 1) -#define MDF_CONNECTED_IND (1 << 2) -#define MDF_FULL_SYNC (1 << 3) -#define MDF_WAS_UP_TO_DATE (1 << 4) -#define MDF_PEER_OUT_DATED (1 << 5) -#define MDF_CRASHED_PRIMARY (1 << 6) -#define MDF_AL_CLEAN (1 << 7) -#define MDF_AL_DISABLED (1 << 8) - -#define MAX_PEERS 32 - -enum drbd_uuid_index { - UI_CURRENT, - UI_BITMAP, - UI_HISTORY_START, - UI_HISTORY_END, - UI_SIZE, /* nl-packet: number of dirty bits */ - UI_FLAGS, /* nl-packet: flags */ - UI_EXTENDED_SIZE /* Everything. */ -}; - -#define HISTORY_UUIDS MAX_PEERS - -enum drbd_timeout_flag { - UT_DEFAULT = 0, - UT_DEGRADED = 1, - UT_PEER_OUTDATED = 2, -}; - -enum drbd_notification_type { - NOTIFY_EXISTS, - NOTIFY_CREATE, - NOTIFY_CHANGE, - NOTIFY_DESTROY, - NOTIFY_CALL, - NOTIFY_RESPONSE, - - NOTIFY_CONTINUES = 0x8000, - NOTIFY_FLAGS = NOTIFY_CONTINUES, -}; - -enum drbd_peer_state { - P_INCONSISTENT = 3, - P_OUTDATED = 4, - P_DOWN = 5, - P_PRIMARY = 6, - P_FENCING = 7, -}; - -#define UUID_JUST_CREATED ((__u64)4) - -enum write_ordering_e { - WO_NONE, - WO_DRAIN_IO, - WO_BDEV_FLUSH, - WO_BIO_BARRIER -}; - -/* magic numbers used in meta data and network packets */ -#define DRBD_MAGIC 0x83740267 -#define DRBD_MAGIC_BIG 0x835a -#define DRBD_MAGIC_100 0x8620ec20 - -#define DRBD_MD_MAGIC_07 (DRBD_MAGIC+3) -#define DRBD_MD_MAGIC_08 (DRBD_MAGIC+4) -#define DRBD_MD_MAGIC_84_UNCLEAN (DRBD_MAGIC+5) - - -/* how I came up with this magic? - * base64 decode "actlog==" ;) */ -#define DRBD_AL_MAGIC 0x69cb65a2 - -/* these are of type "int" */ -#define DRBD_MD_INDEX_INTERNAL -1 -#define DRBD_MD_INDEX_FLEX_EXT -2 -#define DRBD_MD_INDEX_FLEX_INT -3 - -#define DRBD_CPU_MASK_SIZE 32 - -#endif diff --git a/include/linux/drbd_config.h b/include/linux/drbd_config.h deleted file mode 100644 index d215365c6bb1..000000000000 --- a/include/linux/drbd_config.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * drbd_config.h - * DRBD's compile time configuration. - */ - -#ifndef DRBD_CONFIG_H -#define DRBD_CONFIG_H - -extern const char *drbd_buildtag(void); - -#define REL_VERSION "8.4.11" -#define PRO_VERSION_MIN 86 -#define PRO_VERSION_MAX 101 - -#endif diff --git a/include/linux/drbd_genl_api.h b/include/linux/drbd_genl_api.h index 70682c058027..19d263924852 100644 --- a/include/linux/drbd_genl_api.h +++ b/include/linux/drbd_genl_api.h @@ -2,46 +2,6 @@ #ifndef DRBD_GENL_STRUCT_H #define DRBD_GENL_STRUCT_H -/** - * struct drbd_genlmsghdr - DRBD specific header used in NETLINK_GENERIC requests - * @minor: - * For admin requests (user -> kernel): which minor device to operate on. - * For (unicast) replies or informational (broadcast) messages - * (kernel -> user): which minor device the information is about. - * If we do not operate on minors, but on connections or resources, - * the minor value shall be (~0), and the attribute DRBD_NLA_CFG_CONTEXT - * is used instead. - * @flags: possible operation modifiers (relevant only for user->kernel): - * DRBD_GENL_F_SET_DEFAULTS - * @volume: - * When creating a new minor (adding it to a resource), the resource needs - * to know which volume number within the resource this is supposed to be. - * The volume number corresponds to the same volume number on the remote side, - * whereas the minor number on the remote side may be different - * (union with flags). - * @ret_code: kernel->userland unicast cfg reply return code (union with flags); - */ -struct drbd_genlmsghdr { - __u32 minor; - union { - __u32 flags; - __s32 ret_code; - }; -}; - -/* To be used in drbd_genlmsghdr.flags */ -enum { - DRBD_GENL_F_SET_DEFAULTS = 1, -}; - -enum drbd_state_info_bcast_reason { - SIB_GET_STATUS_REPLY = 1, - SIB_STATE_CHANGE = 2, - SIB_HELPER_PRE = 3, - SIB_HELPER_POST = 4, - SIB_SYNC_PROGRESS = 5, -}; - /* hack around predefined gcc/cpp "linux=1", * we cannot possibly include <1/drbd_genl.h> */ #undef linux diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h deleted file mode 100644 index 5b042fb427e9..000000000000 --- a/include/linux/drbd_limits.h +++ /dev/null @@ -1,251 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - drbd_limits.h - This file is part of DRBD by Philipp Reisner and Lars Ellenberg. -*/ - -/* - * Our current limitations. - * Some of them are hard limits, - * some of them are arbitrary range limits, that make it easier to provide - * feedback about nonsense settings for certain configurable values. - */ - -#ifndef DRBD_LIMITS_H -#define DRBD_LIMITS_H 1 - -#define DEBUG_RANGE_CHECK 0 - -#define DRBD_MINOR_COUNT_MIN 1U -#define DRBD_MINOR_COUNT_MAX 255U -#define DRBD_MINOR_COUNT_DEF 32U -#define DRBD_MINOR_COUNT_SCALE '1' - -#define DRBD_VOLUME_MAX 65534U - -#define DRBD_DIALOG_REFRESH_MIN 0U -#define DRBD_DIALOG_REFRESH_MAX 600U -#define DRBD_DIALOG_REFRESH_SCALE '1' - -/* valid port number */ -#define DRBD_PORT_MIN 1U -#define DRBD_PORT_MAX 0xffffU -#define DRBD_PORT_SCALE '1' - -/* startup { */ - /* if you want more than 3.4 days, disable */ -#define DRBD_WFC_TIMEOUT_MIN 0U -#define DRBD_WFC_TIMEOUT_MAX 300000U -#define DRBD_WFC_TIMEOUT_DEF 0U -#define DRBD_WFC_TIMEOUT_SCALE '1' - -#define DRBD_DEGR_WFC_TIMEOUT_MIN 0U -#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000U -#define DRBD_DEGR_WFC_TIMEOUT_DEF 0U -#define DRBD_DEGR_WFC_TIMEOUT_SCALE '1' - -#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0U -#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000U -#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0U -#define DRBD_OUTDATED_WFC_TIMEOUT_SCALE '1' -/* }*/ - -/* net { */ - /* timeout, unit centi seconds - * more than one minute timeout is not useful */ -#define DRBD_TIMEOUT_MIN 1U -#define DRBD_TIMEOUT_MAX 600U -#define DRBD_TIMEOUT_DEF 60U /* 6 seconds */ -#define DRBD_TIMEOUT_SCALE '1' - - /* If backing disk takes longer than disk_timeout, mark the disk as failed */ -#define DRBD_DISK_TIMEOUT_MIN 0U /* 0 = disabled */ -#define DRBD_DISK_TIMEOUT_MAX 6000U /* 10 Minutes */ -#define DRBD_DISK_TIMEOUT_DEF 0U /* disabled */ -#define DRBD_DISK_TIMEOUT_SCALE '1' - - /* active connection retries when C_WF_CONNECTION */ -#define DRBD_CONNECT_INT_MIN 1U -#define DRBD_CONNECT_INT_MAX 120U -#define DRBD_CONNECT_INT_DEF 10U /* seconds */ -#define DRBD_CONNECT_INT_SCALE '1' - - /* keep-alive probes when idle */ -#define DRBD_PING_INT_MIN 1U -#define DRBD_PING_INT_MAX 120U -#define DRBD_PING_INT_DEF 10U -#define DRBD_PING_INT_SCALE '1' - - /* timeout for the ping packets.*/ -#define DRBD_PING_TIMEO_MIN 1U -#define DRBD_PING_TIMEO_MAX 300U -#define DRBD_PING_TIMEO_DEF 5U -#define DRBD_PING_TIMEO_SCALE '1' - - /* max number of write requests between write barriers */ -#define DRBD_MAX_EPOCH_SIZE_MIN 1U -#define DRBD_MAX_EPOCH_SIZE_MAX 20000U -#define DRBD_MAX_EPOCH_SIZE_DEF 2048U -#define DRBD_MAX_EPOCH_SIZE_SCALE '1' - - /* I don't think that a tcp send buffer of more than 10M is useful */ -#define DRBD_SNDBUF_SIZE_MIN 0U -#define DRBD_SNDBUF_SIZE_MAX (10U<<20) -#define DRBD_SNDBUF_SIZE_DEF 0U -#define DRBD_SNDBUF_SIZE_SCALE '1' - -#define DRBD_RCVBUF_SIZE_MIN 0U -#define DRBD_RCVBUF_SIZE_MAX (10U<<20) -#define DRBD_RCVBUF_SIZE_DEF 0U -#define DRBD_RCVBUF_SIZE_SCALE '1' - - /* @4k PageSize -> 128kB - 512MB */ -#define DRBD_MAX_BUFFERS_MIN 32U -#define DRBD_MAX_BUFFERS_MAX 131072U -#define DRBD_MAX_BUFFERS_DEF 2048U -#define DRBD_MAX_BUFFERS_SCALE '1' - - /* @4k PageSize -> 4kB - 512MB */ -#define DRBD_UNPLUG_WATERMARK_MIN 1U -#define DRBD_UNPLUG_WATERMARK_MAX 131072U -#define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16) -#define DRBD_UNPLUG_WATERMARK_SCALE '1' - - /* 0 is disabled. - * 200 should be more than enough even for very short timeouts */ -#define DRBD_KO_COUNT_MIN 0U -#define DRBD_KO_COUNT_MAX 200U -#define DRBD_KO_COUNT_DEF 7U -#define DRBD_KO_COUNT_SCALE '1' -/* } */ - -/* syncer { */ - /* FIXME allow rate to be zero? */ -#define DRBD_RESYNC_RATE_MIN 1U -/* channel bonding 10 GbE, or other hardware */ -#define DRBD_RESYNC_RATE_MAX (4 << 20) -#define DRBD_RESYNC_RATE_DEF 250U -#define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ - -#define DRBD_AL_EXTENTS_MIN 67U - /* we use u16 as "slot number", (u16)~0 is "FREE". - * If you use >= 292 kB on-disk ring buffer, - * this is the maximum you can use: */ -#define DRBD_AL_EXTENTS_MAX 0xfffeU -#define DRBD_AL_EXTENTS_DEF 1237U -#define DRBD_AL_EXTENTS_SCALE '1' - -#define DRBD_MINOR_NUMBER_MIN -1 -#define DRBD_MINOR_NUMBER_MAX ((1 << 20) - 1) -#define DRBD_MINOR_NUMBER_DEF -1 -#define DRBD_MINOR_NUMBER_SCALE '1' - -/* } */ - -/* drbdsetup XY resize -d Z - * you are free to reduce the device size to nothing, if you want to. - * the upper limit with 64bit kernel, enough ram and flexible meta data - * is 1 PiB, currently. */ -/* DRBD_MAX_SECTORS */ -#define DRBD_DISK_SIZE_MIN 0LLU -#define DRBD_DISK_SIZE_MAX (1LLU * (2LLU << 40)) -#define DRBD_DISK_SIZE_DEF 0LLU /* = disabled = no user size... */ -#define DRBD_DISK_SIZE_SCALE 's' /* sectors */ - -#define DRBD_ON_IO_ERROR_DEF EP_DETACH -#define DRBD_FENCING_DEF FP_DONT_CARE -#define DRBD_AFTER_SB_0P_DEF ASB_DISCONNECT -#define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT -#define DRBD_AFTER_SB_2P_DEF ASB_DISCONNECT -#define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT -#define DRBD_ON_NO_DATA_DEF OND_IO_ERROR -#define DRBD_ON_CONGESTION_DEF OC_BLOCK -#define DRBD_READ_BALANCING_DEF RB_PREFER_LOCAL - -#define DRBD_MAX_BIO_BVECS_MIN 0U -#define DRBD_MAX_BIO_BVECS_MAX 128U -#define DRBD_MAX_BIO_BVECS_DEF 0U -#define DRBD_MAX_BIO_BVECS_SCALE '1' - -#define DRBD_C_PLAN_AHEAD_MIN 0U -#define DRBD_C_PLAN_AHEAD_MAX 300U -#define DRBD_C_PLAN_AHEAD_DEF 20U -#define DRBD_C_PLAN_AHEAD_SCALE '1' - -#define DRBD_C_DELAY_TARGET_MIN 1U -#define DRBD_C_DELAY_TARGET_MAX 100U -#define DRBD_C_DELAY_TARGET_DEF 10U -#define DRBD_C_DELAY_TARGET_SCALE '1' - -#define DRBD_C_FILL_TARGET_MIN 0U -#define DRBD_C_FILL_TARGET_MAX (1U<<20) /* 500MByte in sec */ -#define DRBD_C_FILL_TARGET_DEF 100U /* Try to place 50KiB in socket send buffer during resync */ -#define DRBD_C_FILL_TARGET_SCALE 's' /* sectors */ - -#define DRBD_C_MAX_RATE_MIN 250U -#define DRBD_C_MAX_RATE_MAX (4U << 20) -#define DRBD_C_MAX_RATE_DEF 102400U -#define DRBD_C_MAX_RATE_SCALE 'k' /* kilobytes */ - -#define DRBD_C_MIN_RATE_MIN 0U -#define DRBD_C_MIN_RATE_MAX (4U << 20) -#define DRBD_C_MIN_RATE_DEF 250U -#define DRBD_C_MIN_RATE_SCALE 'k' /* kilobytes */ - -#define DRBD_CONG_FILL_MIN 0U -#define DRBD_CONG_FILL_MAX (10U<<21) /* 10GByte in sectors */ -#define DRBD_CONG_FILL_DEF 0U -#define DRBD_CONG_FILL_SCALE 's' /* sectors */ - -#define DRBD_CONG_EXTENTS_MIN DRBD_AL_EXTENTS_MIN -#define DRBD_CONG_EXTENTS_MAX DRBD_AL_EXTENTS_MAX -#define DRBD_CONG_EXTENTS_DEF DRBD_AL_EXTENTS_DEF -#define DRBD_CONG_EXTENTS_SCALE DRBD_AL_EXTENTS_SCALE - -#define DRBD_PROTOCOL_DEF DRBD_PROT_C - -#define DRBD_DISK_BARRIER_DEF 0U -#define DRBD_DISK_FLUSHES_DEF 1U -#define DRBD_DISK_DRAIN_DEF 1U -#define DRBD_MD_FLUSHES_DEF 1U -#define DRBD_TCP_CORK_DEF 1U -#define DRBD_AL_UPDATES_DEF 1U - -/* We used to ignore the discard_zeroes_data setting. - * To not change established (and expected) behaviour, - * by default assume that, for discard_zeroes_data=0, - * we can make that an effective discard_zeroes_data=1, - * if we only explicitly zero-out unaligned partial chunks. */ -#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1U - -/* Some backends pretend to support WRITE SAME, - * but fail such requests when they are actually submitted. - * This is to tell DRBD to not even try. */ -#define DRBD_DISABLE_WRITE_SAME_DEF 0U - -#define DRBD_ALLOW_TWO_PRIMARIES_DEF 0U -#define DRBD_ALWAYS_ASBP_DEF 0U -#define DRBD_USE_RLE_DEF 1U -#define DRBD_CSUMS_AFTER_CRASH_ONLY_DEF 0U - -#define DRBD_AL_STRIPES_MIN 1U -#define DRBD_AL_STRIPES_MAX 1024U -#define DRBD_AL_STRIPES_DEF 1U -#define DRBD_AL_STRIPES_SCALE '1' - -#define DRBD_AL_STRIPE_SIZE_MIN 4U -#define DRBD_AL_STRIPE_SIZE_MAX 16777216U -#define DRBD_AL_STRIPE_SIZE_DEF 32U -#define DRBD_AL_STRIPE_SIZE_SCALE 'k' /* kilobytes */ - -#define DRBD_SOCKET_CHECK_TIMEO_MIN 0U -#define DRBD_SOCKET_CHECK_TIMEO_MAX DRBD_PING_TIMEO_MAX -#define DRBD_SOCKET_CHECK_TIMEO_DEF 0U -#define DRBD_SOCKET_CHECK_TIMEO_SCALE '1' - -#define DRBD_RS_DISCARD_GRANULARITY_MIN 0U -#define DRBD_RS_DISCARD_GRANULARITY_MAX (1U<<20) /* 1MiByte */ -#define DRBD_RS_DISCARD_GRANULARITY_DEF 0U /* disabled by default */ -#define DRBD_RS_DISCARD_GRANULARITY_SCALE '1' /* bytes */ - -#endif diff --git a/include/uapi/linux/drbd.h b/include/uapi/linux/drbd.h new file mode 100644 index 000000000000..7930a972d8a4 --- /dev/null +++ b/include/uapi/linux/drbd.h @@ -0,0 +1,432 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */ +/* + drbd.h + Kernel module for 2.6.x Kernels + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2001-2008, Philipp Reisner . + Copyright (C) 2001-2008, Lars Ellenberg . + + +*/ +#ifndef DRBD_H +#define DRBD_H +#include + +#ifdef __KERNEL__ +#include +#include +#else +#include +#include +#include + +/* Although the Linux source code makes a difference between + generic endianness and the bitfields' endianness, there is no + architecture as of Linux-2.6.24-rc4 where the bitfields' endianness + does not match the generic endianness. */ + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define __LITTLE_ENDIAN_BITFIELD +#elif __BYTE_ORDER == __BIG_ENDIAN +#define __BIG_ENDIAN_BITFIELD +#else +# error "sorry, weird endianness on this box" +#endif + +#endif + +enum drbd_io_error_p { + EP_PASS_ON, /* FIXME should the better be named "Ignore"? */ + EP_CALL_HELPER, + EP_DETACH +}; + +enum drbd_fencing_p { + FP_NOT_AVAIL = -1, /* Not a policy */ + FP_DONT_CARE = 0, + FP_RESOURCE, + FP_STONITH +}; + +enum drbd_disconnect_p { + DP_RECONNECT, + DP_DROP_NET_CONF, + DP_FREEZE_IO +}; + +enum drbd_after_sb_p { + ASB_DISCONNECT, + ASB_DISCARD_YOUNGER_PRI, + ASB_DISCARD_OLDER_PRI, + ASB_DISCARD_ZERO_CHG, + ASB_DISCARD_LEAST_CHG, + ASB_DISCARD_LOCAL, + ASB_DISCARD_REMOTE, + ASB_CONSENSUS, + ASB_DISCARD_SECONDARY, + ASB_CALL_HELPER, + ASB_VIOLENTLY +}; + +enum drbd_on_no_data { + OND_IO_ERROR, + OND_SUSPEND_IO +}; + +enum drbd_on_congestion { + OC_BLOCK, + OC_PULL_AHEAD, + OC_DISCONNECT, +}; + +enum drbd_read_balancing { + RB_PREFER_LOCAL, + RB_PREFER_REMOTE, + RB_ROUND_ROBIN, + RB_LEAST_PENDING, + RB_CONGESTED_REMOTE, + RB_32K_STRIPING, + RB_64K_STRIPING, + RB_128K_STRIPING, + RB_256K_STRIPING, + RB_512K_STRIPING, + RB_1M_STRIPING, +}; + +/* KEEP the order, do not delete or insert. Only append. */ +enum drbd_ret_code { + ERR_CODE_BASE = 100, + NO_ERROR = 101, + ERR_LOCAL_ADDR = 102, + ERR_PEER_ADDR = 103, + ERR_OPEN_DISK = 104, + ERR_OPEN_MD_DISK = 105, + ERR_DISK_NOT_BDEV = 107, + ERR_MD_NOT_BDEV = 108, + ERR_DISK_TOO_SMALL = 111, + ERR_MD_DISK_TOO_SMALL = 112, + ERR_BDCLAIM_DISK = 114, + ERR_BDCLAIM_MD_DISK = 115, + ERR_MD_IDX_INVALID = 116, + ERR_IO_MD_DISK = 118, + ERR_MD_INVALID = 119, + ERR_AUTH_ALG = 120, + ERR_AUTH_ALG_ND = 121, + ERR_NOMEM = 122, + ERR_DISCARD_IMPOSSIBLE = 123, + ERR_DISK_CONFIGURED = 124, + ERR_NET_CONFIGURED = 125, + ERR_MANDATORY_TAG = 126, + ERR_MINOR_INVALID = 127, + ERR_INTR = 129, /* EINTR */ + ERR_RESIZE_RESYNC = 130, + ERR_NO_PRIMARY = 131, + ERR_RESYNC_AFTER = 132, + ERR_RESYNC_AFTER_CYCLE = 133, + ERR_PAUSE_IS_SET = 134, + ERR_PAUSE_IS_CLEAR = 135, + ERR_PACKET_NR = 137, + ERR_NO_DISK = 138, + ERR_NOT_PROTO_C = 139, + ERR_NOMEM_BITMAP = 140, + ERR_INTEGRITY_ALG = 141, /* DRBD 8.2 only */ + ERR_INTEGRITY_ALG_ND = 142, /* DRBD 8.2 only */ + ERR_CPU_MASK_PARSE = 143, /* DRBD 8.2 only */ + ERR_CSUMS_ALG = 144, /* DRBD 8.2 only */ + ERR_CSUMS_ALG_ND = 145, /* DRBD 8.2 only */ + ERR_VERIFY_ALG = 146, /* DRBD 8.2 only */ + ERR_VERIFY_ALG_ND = 147, /* DRBD 8.2 only */ + ERR_CSUMS_RESYNC_RUNNING= 148, /* DRBD 8.2 only */ + ERR_VERIFY_RUNNING = 149, /* DRBD 8.2 only */ + ERR_DATA_NOT_CURRENT = 150, + ERR_CONNECTED = 151, /* DRBD 8.3 only */ + ERR_PERM = 152, + ERR_NEED_APV_93 = 153, + ERR_STONITH_AND_PROT_A = 154, + ERR_CONG_NOT_PROTO_A = 155, + ERR_PIC_AFTER_DEP = 156, + ERR_PIC_PEER_DEP = 157, + ERR_RES_NOT_KNOWN = 158, + ERR_RES_IN_USE = 159, + ERR_MINOR_CONFIGURED = 160, + ERR_MINOR_OR_VOLUME_EXISTS = 161, + ERR_INVALID_REQUEST = 162, + ERR_NEED_APV_100 = 163, + ERR_NEED_ALLOW_TWO_PRI = 164, + ERR_MD_UNCLEAN = 165, + ERR_MD_LAYOUT_CONNECTED = 166, + ERR_MD_LAYOUT_TOO_BIG = 167, + ERR_MD_LAYOUT_TOO_SMALL = 168, + ERR_MD_LAYOUT_NO_FIT = 169, + ERR_IMPLICIT_SHRINK = 170, + /* insert new ones above this line */ + AFTER_LAST_ERR_CODE +}; + +#define DRBD_PROT_A 1 +#define DRBD_PROT_B 2 +#define DRBD_PROT_C 3 + +enum drbd_role { + R_UNKNOWN = 0, + R_PRIMARY = 1, /* role */ + R_SECONDARY = 2, /* role */ + R_MASK = 3, +}; + +/* The order of these constants is important. + * The lower ones (=C_WF_REPORT_PARAMS ==> There is a socket + */ +enum drbd_conns { + C_STANDALONE, + C_DISCONNECTING, /* Temporal state on the way to StandAlone. */ + C_UNCONNECTED, /* >= C_UNCONNECTED -> inc_net() succeeds */ + + /* These temporal states are all used on the way + * from >= C_CONNECTED to Unconnected. + * The 'disconnect reason' states + * I do not allow to change between them. */ + C_TIMEOUT, + C_BROKEN_PIPE, + C_NETWORK_FAILURE, + C_PROTOCOL_ERROR, + C_TEAR_DOWN, + + C_WF_CONNECTION, + C_WF_REPORT_PARAMS, /* we have a socket */ + C_CONNECTED, /* we have introduced each other */ + C_STARTING_SYNC_S, /* starting full sync by admin request. */ + C_STARTING_SYNC_T, /* starting full sync by admin request. */ + C_WF_BITMAP_S, + C_WF_BITMAP_T, + C_WF_SYNC_UUID, + + /* All SyncStates are tested with this comparison + * xx >= C_SYNC_SOURCE && xx <= C_PAUSED_SYNC_T */ + C_SYNC_SOURCE, + C_SYNC_TARGET, + C_VERIFY_S, + C_VERIFY_T, + C_PAUSED_SYNC_S, + C_PAUSED_SYNC_T, + + C_AHEAD, + C_BEHIND, + + C_MASK = 31 +}; + +enum drbd_disk_state { + D_DISKLESS, + D_ATTACHING, /* In the process of reading the meta-data */ + D_FAILED, /* Becomes D_DISKLESS as soon as we told it the peer */ + /* when >= D_FAILED it is legal to access mdev->ldev */ + D_NEGOTIATING, /* Late attaching state, we need to talk to the peer */ + D_INCONSISTENT, + D_OUTDATED, + D_UNKNOWN, /* Only used for the peer, never for myself */ + D_CONSISTENT, /* Might be D_OUTDATED, might be D_UP_TO_DATE ... */ + D_UP_TO_DATE, /* Only this disk state allows applications' IO ! */ + D_MASK = 15 +}; + +union drbd_state { +/* According to gcc's docs is the ... + * The order of allocation of bit-fields within a unit (C90 6.5.2.1, C99 6.7.2.1). + * Determined by ABI. + * pointed out by Maxim Uvarov q + * even though we transmit as "cpu_to_be32(state)", + * the offsets of the bitfields still need to be swapped + * on different endianness. + */ + struct { +#if defined(__LITTLE_ENDIAN_BITFIELD) + unsigned role:2 ; /* 3/4 primary/secondary/unknown */ + unsigned peer:2 ; /* 3/4 primary/secondary/unknown */ + unsigned conn:5 ; /* 17/32 cstates */ + unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned susp:1 ; /* 2/2 IO suspended no/yes (by user) */ + unsigned aftr_isp:1 ; /* isp .. imposed sync pause */ + unsigned peer_isp:1 ; + unsigned user_isp:1 ; + unsigned susp_nod:1 ; /* IO suspended because no data */ + unsigned susp_fen:1 ; /* IO suspended because fence peer handler runs*/ + unsigned _pad:9; /* 0 unused */ +#elif defined(__BIG_ENDIAN_BITFIELD) + unsigned _pad:9; + unsigned susp_fen:1 ; + unsigned susp_nod:1 ; + unsigned user_isp:1 ; + unsigned peer_isp:1 ; + unsigned aftr_isp:1 ; /* isp .. imposed sync pause */ + unsigned susp:1 ; /* 2/2 IO suspended no/yes */ + unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned conn:5 ; /* 17/32 cstates */ + unsigned peer:2 ; /* 3/4 primary/secondary/unknown */ + unsigned role:2 ; /* 3/4 primary/secondary/unknown */ +#else +# error "this endianness is not supported" +#endif + }; + unsigned int i; +}; + +enum drbd_state_rv { + SS_CW_NO_NEED = 4, + SS_CW_SUCCESS = 3, + SS_NOTHING_TO_DO = 2, + SS_SUCCESS = 1, + SS_UNKNOWN_ERROR = 0, /* Used to sleep longer in _drbd_request_state */ + SS_TWO_PRIMARIES = -1, + SS_NO_UP_TO_DATE_DISK = -2, + SS_NO_LOCAL_DISK = -4, + SS_NO_REMOTE_DISK = -5, + SS_CONNECTED_OUTDATES = -6, + SS_PRIMARY_NOP = -7, + SS_RESYNC_RUNNING = -8, + SS_ALREADY_STANDALONE = -9, + SS_CW_FAILED_BY_PEER = -10, + SS_IS_DISKLESS = -11, + SS_DEVICE_IN_USE = -12, + SS_NO_NET_CONFIG = -13, + SS_NO_VERIFY_ALG = -14, /* drbd-8.2 only */ + SS_NEED_CONNECTION = -15, /* drbd-8.2 only */ + SS_LOWER_THAN_OUTDATED = -16, + SS_NOT_SUPPORTED = -17, /* drbd-8.2 only */ + SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ + SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ + SS_O_VOL_PEER_PRI = -20, + SS_OUTDATE_WO_CONN = -21, + SS_AFTER_LAST_ERROR = -22, /* Keep this at bottom */ +}; + +#define SHARED_SECRET_MAX 64 + +#define MDF_CONSISTENT (1 << 0) +#define MDF_PRIMARY_IND (1 << 1) +#define MDF_CONNECTED_IND (1 << 2) +#define MDF_FULL_SYNC (1 << 3) +#define MDF_WAS_UP_TO_DATE (1 << 4) +#define MDF_PEER_OUT_DATED (1 << 5) +#define MDF_CRASHED_PRIMARY (1 << 6) +#define MDF_AL_CLEAN (1 << 7) +#define MDF_AL_DISABLED (1 << 8) + +#define MAX_PEERS 32 + +enum drbd_uuid_index { + UI_CURRENT, + UI_BITMAP, + UI_HISTORY_START, + UI_HISTORY_END, + UI_SIZE, /* nl-packet: number of dirty bits */ + UI_FLAGS, /* nl-packet: flags */ + UI_EXTENDED_SIZE /* Everything. */ +}; + +#define HISTORY_UUIDS MAX_PEERS + +enum drbd_timeout_flag { + UT_DEFAULT = 0, + UT_DEGRADED = 1, + UT_PEER_OUTDATED = 2, +}; + +enum drbd_notification_type { + NOTIFY_EXISTS, + NOTIFY_CREATE, + NOTIFY_CHANGE, + NOTIFY_DESTROY, + NOTIFY_CALL, + NOTIFY_RESPONSE, + + NOTIFY_CONTINUES = 0x8000, + NOTIFY_FLAGS = NOTIFY_CONTINUES, +}; + +enum drbd_peer_state { + P_INCONSISTENT = 3, + P_OUTDATED = 4, + P_DOWN = 5, + P_PRIMARY = 6, + P_FENCING = 7, +}; + +#define UUID_JUST_CREATED ((__u64)4) + +enum write_ordering_e { + WO_NONE, + WO_DRAIN_IO, + WO_BDEV_FLUSH, + WO_BIO_BARRIER +}; + +/* magic numbers used in meta data and network packets */ +#define DRBD_MAGIC 0x83740267 +#define DRBD_MAGIC_BIG 0x835a +#define DRBD_MAGIC_100 0x8620ec20 + +#define DRBD_MD_MAGIC_07 (DRBD_MAGIC+3) +#define DRBD_MD_MAGIC_08 (DRBD_MAGIC+4) +#define DRBD_MD_MAGIC_84_UNCLEAN (DRBD_MAGIC+5) + + +/* how I came up with this magic? + * base64 decode "actlog==" ;) */ +#define DRBD_AL_MAGIC 0x69cb65a2 + +/* these are of type "int" */ +#define DRBD_MD_INDEX_INTERNAL -1 +#define DRBD_MD_INDEX_FLEX_EXT -2 +#define DRBD_MD_INDEX_FLEX_INT -3 + +#define DRBD_CPU_MASK_SIZE 32 + +/** + * struct drbd_genlmsghdr - DRBD specific header used in NETLINK_GENERIC requests + * @minor: + * For admin requests (user -> kernel): which minor device to operate on. + * For (unicast) replies or informational (broadcast) messages + * (kernel -> user): which minor device the information is about. + * If we do not operate on minors, but on connections or resources, + * the minor value shall be (~0), and the attribute DRBD_NLA_CFG_CONTEXT + * is used instead. + * @flags: possible operation modifiers (relevant only for user->kernel): + * DRBD_GENL_F_SET_DEFAULTS + * @volume: + * When creating a new minor (adding it to a resource), the resource needs + * to know which volume number within the resource this is supposed to be. + * The volume number corresponds to the same volume number on the remote side, + * whereas the minor number on the remote side may be different + * (union with flags). + * @ret_code: kernel->userland unicast cfg reply return code (union with flags); + */ +struct drbd_genlmsghdr { + __u32 minor; + union { + __u32 flags; + __s32 ret_code; + }; +}; + +/* To be used in drbd_genlmsghdr.flags */ +enum { + DRBD_GENL_F_SET_DEFAULTS = 1, +}; + +enum drbd_state_info_bcast_reason { + SIB_GET_STATUS_REPLY = 1, + SIB_STATE_CHANGE = 2, + SIB_HELPER_PRE = 3, + SIB_HELPER_POST = 4, + SIB_SYNC_PROGRESS = 5, +}; + +#endif diff --git a/include/uapi/linux/drbd_limits.h b/include/uapi/linux/drbd_limits.h new file mode 100644 index 000000000000..a72a102d1ca7 --- /dev/null +++ b/include/uapi/linux/drbd_limits.h @@ -0,0 +1,251 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + drbd_limits.h + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. +*/ + +/* + * Our current limitations. + * Some of them are hard limits, + * some of them are arbitrary range limits, that make it easier to provide + * feedback about nonsense settings for certain configurable values. + */ + +#ifndef DRBD_LIMITS_H +#define DRBD_LIMITS_H 1 + +#define DEBUG_RANGE_CHECK 0 + +#define DRBD_MINOR_COUNT_MIN 1U +#define DRBD_MINOR_COUNT_MAX 255U +#define DRBD_MINOR_COUNT_DEF 32U +#define DRBD_MINOR_COUNT_SCALE '1' + +#define DRBD_VOLUME_MAX 65534U + +#define DRBD_DIALOG_REFRESH_MIN 0U +#define DRBD_DIALOG_REFRESH_MAX 600U +#define DRBD_DIALOG_REFRESH_SCALE '1' + +/* valid port number */ +#define DRBD_PORT_MIN 1U +#define DRBD_PORT_MAX 0xffffU +#define DRBD_PORT_SCALE '1' + +/* startup { */ + /* if you want more than 3.4 days, disable */ +#define DRBD_WFC_TIMEOUT_MIN 0U +#define DRBD_WFC_TIMEOUT_MAX 300000U +#define DRBD_WFC_TIMEOUT_DEF 0U +#define DRBD_WFC_TIMEOUT_SCALE '1' + +#define DRBD_DEGR_WFC_TIMEOUT_MIN 0U +#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000U +#define DRBD_DEGR_WFC_TIMEOUT_DEF 0U +#define DRBD_DEGR_WFC_TIMEOUT_SCALE '1' + +#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0U +#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000U +#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0U +#define DRBD_OUTDATED_WFC_TIMEOUT_SCALE '1' +/* }*/ + +/* net { */ + /* timeout, unit centi seconds + * more than one minute timeout is not useful */ +#define DRBD_TIMEOUT_MIN 1U +#define DRBD_TIMEOUT_MAX 600U +#define DRBD_TIMEOUT_DEF 60U /* 6 seconds */ +#define DRBD_TIMEOUT_SCALE '1' + + /* If backing disk takes longer than disk_timeout, mark the disk as failed */ +#define DRBD_DISK_TIMEOUT_MIN 0U /* 0 = disabled */ +#define DRBD_DISK_TIMEOUT_MAX 6000U /* 10 Minutes */ +#define DRBD_DISK_TIMEOUT_DEF 0U /* disabled */ +#define DRBD_DISK_TIMEOUT_SCALE '1' + + /* active connection retries when C_WF_CONNECTION */ +#define DRBD_CONNECT_INT_MIN 1U +#define DRBD_CONNECT_INT_MAX 120U +#define DRBD_CONNECT_INT_DEF 10U /* seconds */ +#define DRBD_CONNECT_INT_SCALE '1' + + /* keep-alive probes when idle */ +#define DRBD_PING_INT_MIN 1U +#define DRBD_PING_INT_MAX 120U +#define DRBD_PING_INT_DEF 10U +#define DRBD_PING_INT_SCALE '1' + + /* timeout for the ping packets.*/ +#define DRBD_PING_TIMEO_MIN 1U +#define DRBD_PING_TIMEO_MAX 300U +#define DRBD_PING_TIMEO_DEF 5U +#define DRBD_PING_TIMEO_SCALE '1' + + /* max number of write requests between write barriers */ +#define DRBD_MAX_EPOCH_SIZE_MIN 1U +#define DRBD_MAX_EPOCH_SIZE_MAX 20000U +#define DRBD_MAX_EPOCH_SIZE_DEF 2048U +#define DRBD_MAX_EPOCH_SIZE_SCALE '1' + + /* I don't think that a tcp send buffer of more than 10M is useful */ +#define DRBD_SNDBUF_SIZE_MIN 0U +#define DRBD_SNDBUF_SIZE_MAX (10U<<20) +#define DRBD_SNDBUF_SIZE_DEF 0U +#define DRBD_SNDBUF_SIZE_SCALE '1' + +#define DRBD_RCVBUF_SIZE_MIN 0U +#define DRBD_RCVBUF_SIZE_MAX (10U<<20) +#define DRBD_RCVBUF_SIZE_DEF 0U +#define DRBD_RCVBUF_SIZE_SCALE '1' + + /* @4k PageSize -> 128kB - 512MB */ +#define DRBD_MAX_BUFFERS_MIN 32U +#define DRBD_MAX_BUFFERS_MAX 131072U +#define DRBD_MAX_BUFFERS_DEF 2048U +#define DRBD_MAX_BUFFERS_SCALE '1' + + /* @4k PageSize -> 4kB - 512MB */ +#define DRBD_UNPLUG_WATERMARK_MIN 1U +#define DRBD_UNPLUG_WATERMARK_MAX 131072U +#define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16) +#define DRBD_UNPLUG_WATERMARK_SCALE '1' + + /* 0 is disabled. + * 200 should be more than enough even for very short timeouts */ +#define DRBD_KO_COUNT_MIN 0U +#define DRBD_KO_COUNT_MAX 200U +#define DRBD_KO_COUNT_DEF 7U +#define DRBD_KO_COUNT_SCALE '1' +/* } */ + +/* syncer { */ + /* FIXME allow rate to be zero? */ +#define DRBD_RESYNC_RATE_MIN 1U +/* channel bonding 10 GbE, or other hardware */ +#define DRBD_RESYNC_RATE_MAX (4 << 20) +#define DRBD_RESYNC_RATE_DEF 250U +#define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ + +#define DRBD_AL_EXTENTS_MIN 67U + /* we use u16 as "slot number", (u16)~0 is "FREE". + * If you use >= 292 kB on-disk ring buffer, + * this is the maximum you can use: */ +#define DRBD_AL_EXTENTS_MAX 0xfffeU +#define DRBD_AL_EXTENTS_DEF 1237U +#define DRBD_AL_EXTENTS_SCALE '1' + +#define DRBD_MINOR_NUMBER_MIN -1 +#define DRBD_MINOR_NUMBER_MAX ((1 << 20) - 1) +#define DRBD_MINOR_NUMBER_DEF -1 +#define DRBD_MINOR_NUMBER_SCALE '1' + +/* } */ + +/* drbdsetup XY resize -d Z + * you are free to reduce the device size to nothing, if you want to. + * the upper limit with 64bit kernel, enough ram and flexible meta data + * is 1 PiB, currently. */ +/* DRBD_MAX_SECTORS */ +#define DRBD_DISK_SIZE_MIN 0LLU +#define DRBD_DISK_SIZE_MAX (1LLU * (2LLU << 40)) +#define DRBD_DISK_SIZE_DEF 0LLU /* = disabled = no user size... */ +#define DRBD_DISK_SIZE_SCALE 's' /* sectors */ + +#define DRBD_ON_IO_ERROR_DEF EP_DETACH +#define DRBD_FENCING_DEF FP_DONT_CARE +#define DRBD_AFTER_SB_0P_DEF ASB_DISCONNECT +#define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT +#define DRBD_AFTER_SB_2P_DEF ASB_DISCONNECT +#define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT +#define DRBD_ON_NO_DATA_DEF OND_IO_ERROR +#define DRBD_ON_CONGESTION_DEF OC_BLOCK +#define DRBD_READ_BALANCING_DEF RB_PREFER_LOCAL + +#define DRBD_MAX_BIO_BVECS_MIN 0U +#define DRBD_MAX_BIO_BVECS_MAX 128U +#define DRBD_MAX_BIO_BVECS_DEF 0U +#define DRBD_MAX_BIO_BVECS_SCALE '1' + +#define DRBD_C_PLAN_AHEAD_MIN 0U +#define DRBD_C_PLAN_AHEAD_MAX 300U +#define DRBD_C_PLAN_AHEAD_DEF 20U +#define DRBD_C_PLAN_AHEAD_SCALE '1' + +#define DRBD_C_DELAY_TARGET_MIN 1U +#define DRBD_C_DELAY_TARGET_MAX 100U +#define DRBD_C_DELAY_TARGET_DEF 10U +#define DRBD_C_DELAY_TARGET_SCALE '1' + +#define DRBD_C_FILL_TARGET_MIN 0U +#define DRBD_C_FILL_TARGET_MAX (1U<<20) /* 500MByte in sec */ +#define DRBD_C_FILL_TARGET_DEF 100U /* Try to place 50KiB in socket send buffer during resync */ +#define DRBD_C_FILL_TARGET_SCALE 's' /* sectors */ + +#define DRBD_C_MAX_RATE_MIN 250U +#define DRBD_C_MAX_RATE_MAX (4U << 20) +#define DRBD_C_MAX_RATE_DEF 102400U +#define DRBD_C_MAX_RATE_SCALE 'k' /* kilobytes */ + +#define DRBD_C_MIN_RATE_MIN 0U +#define DRBD_C_MIN_RATE_MAX (4U << 20) +#define DRBD_C_MIN_RATE_DEF 250U +#define DRBD_C_MIN_RATE_SCALE 'k' /* kilobytes */ + +#define DRBD_CONG_FILL_MIN 0U +#define DRBD_CONG_FILL_MAX (10U<<21) /* 10GByte in sectors */ +#define DRBD_CONG_FILL_DEF 0U +#define DRBD_CONG_FILL_SCALE 's' /* sectors */ + +#define DRBD_CONG_EXTENTS_MIN DRBD_AL_EXTENTS_MIN +#define DRBD_CONG_EXTENTS_MAX DRBD_AL_EXTENTS_MAX +#define DRBD_CONG_EXTENTS_DEF DRBD_AL_EXTENTS_DEF +#define DRBD_CONG_EXTENTS_SCALE DRBD_AL_EXTENTS_SCALE + +#define DRBD_PROTOCOL_DEF DRBD_PROT_C + +#define DRBD_DISK_BARRIER_DEF 0U +#define DRBD_DISK_FLUSHES_DEF 1U +#define DRBD_DISK_DRAIN_DEF 1U +#define DRBD_MD_FLUSHES_DEF 1U +#define DRBD_TCP_CORK_DEF 1U +#define DRBD_AL_UPDATES_DEF 1U + +/* We used to ignore the discard_zeroes_data setting. + * To not change established (and expected) behaviour, + * by default assume that, for discard_zeroes_data=0, + * we can make that an effective discard_zeroes_data=1, + * if we only explicitly zero-out unaligned partial chunks. */ +#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1U + +/* Some backends pretend to support WRITE SAME, + * but fail such requests when they are actually submitted. + * This is to tell DRBD to not even try. */ +#define DRBD_DISABLE_WRITE_SAME_DEF 0U + +#define DRBD_ALLOW_TWO_PRIMARIES_DEF 0U +#define DRBD_ALWAYS_ASBP_DEF 0U +#define DRBD_USE_RLE_DEF 1U +#define DRBD_CSUMS_AFTER_CRASH_ONLY_DEF 0U + +#define DRBD_AL_STRIPES_MIN 1U +#define DRBD_AL_STRIPES_MAX 1024U +#define DRBD_AL_STRIPES_DEF 1U +#define DRBD_AL_STRIPES_SCALE '1' + +#define DRBD_AL_STRIPE_SIZE_MIN 4U +#define DRBD_AL_STRIPE_SIZE_MAX 16777216U +#define DRBD_AL_STRIPE_SIZE_DEF 32U +#define DRBD_AL_STRIPE_SIZE_SCALE 'k' /* kilobytes */ + +#define DRBD_SOCKET_CHECK_TIMEO_MIN 0U +#define DRBD_SOCKET_CHECK_TIMEO_MAX DRBD_PING_TIMEO_MAX +#define DRBD_SOCKET_CHECK_TIMEO_DEF 0U +#define DRBD_SOCKET_CHECK_TIMEO_SCALE '1' + +#define DRBD_RS_DISCARD_GRANULARITY_MIN 0U +#define DRBD_RS_DISCARD_GRANULARITY_MAX (1U<<20) /* 1MiByte */ +#define DRBD_RS_DISCARD_GRANULARITY_DEF 0U /* disabled by default */ +#define DRBD_RS_DISCARD_GRANULARITY_SCALE '1' /* bytes */ + +#endif -- cgit v1.3-14-g43fede From 8098eeb693c4cc4e774c62fbd4875197cb5578ce Mon Sep 17 00:00:00 2001 From: Christoph Böhmwalder Date: Wed, 6 May 2026 14:45:41 +0200 Subject: drbd: replace genl_magic with explicit netlink serialization MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the genl_magic multi-include macro system with explicit serialization and parsing. The *_gen files were initially produced from a YNL spec via a customized ynl-gen-c, but the DRBD netlink family is effectively frozen, so the generator is kept unmodified. All new functionality will land in a separate, properly-designed family. Carry the resulting code as ordinary in-tree source rather than landing the spec and generator changes that produced it. The bulk of the changes are mechanical renames to fit the YNL naming conventions: - Handler functions: drbd_adm_* -> drbd_nl_*_doit/dumpit - GENL_MAGIC_VERSION -> DRBD_FAMILY_VERSION - GENL_MAGIC_FAMILY_HDRSZ -> sizeof(struct drbd_genlmsghdr) - drbd_genl_family -> drbd_nl_family - Attribute IDs: T_* -> DRBD_A_* Remove the nested_attr_tb static global buffer and move to a per-call allocation approach: each deserialization manages its own nested attribute table. This will be needed anyway when we eventually move to parallel_ops, and it's actually simpler this way, so make the move now. Replace the functionality of the "sensitive" flag: this was only used by a single field (shared_secret); open-code redaction logic for that locally. Also replace the "invariant" flag: this only had a couple of users, and those basically never change. Hard code the check directly inline. The genl_family struct itself is defined manually in drbd_nl.c. Also replace a couple of drbd-specific wrappers (nla_put_u64_0pad, drbd_nla_find_nested) with standard kernel functions while we're at it. Finally, completely remove the genl_magic system; DRBD was its only user. Signed-off-by: Christoph Böhmwalder Acked-by: Jakub Kicinski Link: https://patch.msgid.link/20260506124541.1951772-3-christoph.boehmwalder@linbit.com Signed-off-by: Jens Axboe --- drivers/block/drbd/Makefile | 1 + drivers/block/drbd/drbd_debugfs.c | 2 +- drivers/block/drbd/drbd_int.h | 4 +- drivers/block/drbd/drbd_main.c | 6 +- drivers/block/drbd/drbd_nl.c | 416 +++--- drivers/block/drbd/drbd_nl_gen.c | 2606 +++++++++++++++++++++++++++++++++++++ drivers/block/drbd/drbd_nl_gen.h | 395 ++++++ drivers/block/drbd/drbd_proc.c | 2 +- include/linux/drbd_genl.h | 536 -------- include/linux/drbd_genl_api.h | 16 - include/linux/genl_magic_func.h | 413 ------ include/linux/genl_magic_struct.h | 272 ---- include/uapi/linux/drbd.h | 3 + include/uapi/linux/drbd_genl.h | 359 +++++ 14 files changed, 3609 insertions(+), 1422 deletions(-) create mode 100644 drivers/block/drbd/drbd_nl_gen.c create mode 100644 drivers/block/drbd/drbd_nl_gen.h delete mode 100644 include/linux/drbd_genl.h delete mode 100644 include/linux/drbd_genl_api.h delete mode 100644 include/linux/genl_magic_func.h delete mode 100644 include/linux/genl_magic_struct.h create mode 100644 include/uapi/linux/drbd_genl.h (limited to 'include/uapi/linux') diff --git a/drivers/block/drbd/Makefile b/drivers/block/drbd/Makefile index 187eaf81f0f8..5faaa8a8e7f0 100644 --- a/drivers/block/drbd/Makefile +++ b/drivers/block/drbd/Makefile @@ -3,6 +3,7 @@ drbd-y := drbd_buildtag.o drbd_bitmap.o drbd_proc.o drbd-y += drbd_worker.o drbd_receiver.o drbd_req.o drbd_actlog.o drbd-y += drbd_main.o drbd_strings.o drbd_nl.o drbd-y += drbd_interval.o drbd_state.o +drbd-y += drbd_nl_gen.o drbd-$(CONFIG_DEBUG_FS) += drbd_debugfs.o obj-$(CONFIG_BLK_DEV_DRBD) += drbd.o diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c index 12460b584bcb..371abcd7e880 100644 --- a/drivers/block/drbd/drbd_debugfs.c +++ b/drivers/block/drbd/drbd_debugfs.c @@ -844,7 +844,7 @@ static int drbd_version_show(struct seq_file *m, void *ignored) { seq_printf(m, "# %s\n", drbd_buildtag()); seq_printf(m, "VERSION=%s\n", REL_VERSION); - seq_printf(m, "API_VERSION=%u\n", GENL_MAGIC_VERSION); + seq_printf(m, "API_VERSION=%u\n", DRBD_FAMILY_VERSION); seq_printf(m, "PRO_VERSION_MIN=%u\n", PRO_VERSION_MIN); seq_printf(m, "PRO_VERSION_MAX=%u\n", PRO_VERSION_MAX); return 0; diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index f3d746a6d6fd..48b45c3142f7 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -32,14 +32,16 @@ #include #include #include -#include #include #include "drbd_config.h" +#include "drbd_nl_gen.h" #include "drbd_strings.h" #include "drbd_state.h" #include "drbd_protocol.h" #include "drbd_polymorph_printk.h" +extern struct genl_family drbd_nl_family; + /* shared module parameters, defined in drbd_main.c */ #ifdef CONFIG_DRBD_FAULT_INJECTION extern int drbd_enable_faults; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index b1a721dd0496..a2a841c89201 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2324,7 +2324,7 @@ static void drbd_cleanup(void) if (retry.wq) destroy_workqueue(retry.wq); - drbd_genl_unregister(); + genl_unregister_family(&drbd_nl_family); idr_for_each_entry(&drbd_devices, device, i) drbd_delete_device(device); @@ -2846,7 +2846,7 @@ static int __init drbd_init(void) mutex_init(&resources_mutex); INIT_LIST_HEAD(&drbd_resources); - err = drbd_genl_register(); + err = genl_register_family(&drbd_nl_family); if (err) { pr_err("unable to register generic netlink family\n"); goto fail; @@ -2876,7 +2876,7 @@ static int __init drbd_init(void) pr_info("initialized. " "Version: " REL_VERSION " (api:%d/proto:%d-%d)\n", - GENL_MAGIC_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX); + DRBD_FAMILY_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX); pr_info("%s\n", drbd_buildtag()); pr_info("registered as block device major %d\n", DRBD_MAJOR); return 0; /* Success! */ diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index c2ac555473e7..f9ffcd67607b 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -31,59 +31,13 @@ #include -/* .doit */ -// int drbd_adm_create_resource(struct sk_buff *skb, struct genl_info *info); -// int drbd_adm_delete_resource(struct sk_buff *skb, struct genl_info *info); - -int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info); - -int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_down(struct sk_buff *skb, struct genl_info *info); - -int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_pause_sync(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info); -int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info); -/* .dumpit */ -int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb); -int drbd_adm_dump_resources(struct sk_buff *skb, struct netlink_callback *cb); -int drbd_adm_dump_devices(struct sk_buff *skb, struct netlink_callback *cb); -int drbd_adm_dump_devices_done(struct netlink_callback *cb); -int drbd_adm_dump_connections(struct sk_buff *skb, struct netlink_callback *cb); -int drbd_adm_dump_connections_done(struct netlink_callback *cb); -int drbd_adm_dump_peer_devices(struct sk_buff *skb, struct netlink_callback *cb); -int drbd_adm_dump_peer_devices_done(struct netlink_callback *cb); -int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb); - -#include - -static int drbd_pre_doit(const struct genl_split_ops *ops, - struct sk_buff *skb, struct genl_info *info); -static void drbd_post_doit(const struct genl_split_ops *ops, - struct sk_buff *skb, struct genl_info *info); - -#define GENL_MAGIC_FAMILY_PRE_DOIT drbd_pre_doit -#define GENL_MAGIC_FAMILY_POST_DOIT drbd_post_doit - -#include +#include "drbd_nl_gen.h" + +static int drbd_genl_multicast_events(struct sk_buff *skb, gfp_t flags) +{ + return genlmsg_multicast(&drbd_nl_family, skb, 0, + DRBD_NLGRP_EVENTS, flags); +} static atomic_t drbd_genl_seq = ATOMIC_INIT(2); /* two. */ static atomic_t notify_genl_seq = ATOMIC_INIT(2); /* two. */ @@ -114,7 +68,7 @@ static int drbd_msg_put_info(struct sk_buff *skb, const char *info) if (!nla) return err; - err = nla_put_string(skb, T_info_text, info); + err = nla_put_string(skb, DRBD_A_DRBD_CFG_REPLY_INFO_TEXT, info); if (err) { nla_nest_cancel(skb, nla); return err; @@ -135,7 +89,7 @@ static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...) if (!nla) return err; - txt = nla_reserve(skb, T_info_text, 256); + txt = nla_reserve(skb, DRBD_A_DRBD_CFG_REPLY_INFO_TEXT, 256); if (!txt) { nla_nest_cancel(skb, nla); return err; @@ -187,6 +141,15 @@ static const unsigned int drbd_genl_cmd_flags[] = { [DRBD_ADM_DOWN] = DRBD_ADM_NEED_RESOURCE, }; +/* Detect attempts to change invariant attributes in a _change_ handler. */ +#define has_invariant(ntb, attr) \ +({ \ + bool __found = !!(ntb)[attr]; \ + if (__found) \ + pr_info("must not change invariant attr: %s\n", #attr); \ + __found; \ +}) + /* * At this point, we still rely on the global genl_lock(). * If we want to avoid that, and allow "genl_family.parallel_ops", we may need @@ -210,7 +173,7 @@ static int drbd_adm_prepare(struct drbd_config_context *adm_ctx, } adm_ctx->reply_dh = genlmsg_put_reply(adm_ctx->reply_skb, - info, &drbd_genl_family, 0, cmd); + info, &drbd_nl_family, 0, cmd); /* put of a few bytes into a fresh skb of >= 4k will always succeed. * but anyways */ if (!adm_ctx->reply_dh) { @@ -223,9 +186,11 @@ static int drbd_adm_prepare(struct drbd_config_context *adm_ctx, adm_ctx->volume = VOLUME_UNSPECIFIED; if (info->attrs[DRBD_NLA_CFG_CONTEXT]) { + struct nlattr **ntb; struct nlattr *nla; - /* parse and validate only */ - err = drbd_cfg_context_from_attrs(NULL, info); + + /* parse and validate, get nested attribute table */ + err = drbd_cfg_context_ntb_from_attrs(&ntb, info); if (err) goto fail; @@ -234,18 +199,21 @@ static int drbd_adm_prepare(struct drbd_config_context *adm_ctx, err = nla_put_nohdr(adm_ctx->reply_skb, info->attrs[DRBD_NLA_CFG_CONTEXT]->nla_len, info->attrs[DRBD_NLA_CFG_CONTEXT]); - if (err) + if (err) { + kfree(ntb); goto fail; + } /* and assign stuff to the adm_ctx */ - nla = nested_attr_tb[T_ctx_volume]; + nla = ntb[DRBD_A_DRBD_CFG_CONTEXT_CTX_VOLUME]; if (nla) adm_ctx->volume = nla_get_u32(nla); - nla = nested_attr_tb[T_ctx_resource_name]; + nla = ntb[DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME]; if (nla) adm_ctx->resource_name = nla_data(nla); - adm_ctx->my_addr = nested_attr_tb[T_ctx_my_addr]; - adm_ctx->peer_addr = nested_attr_tb[T_ctx_peer_addr]; + adm_ctx->my_addr = ntb[DRBD_A_DRBD_CFG_CONTEXT_CTX_MY_ADDR]; + adm_ctx->peer_addr = ntb[DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR]; + kfree(ntb); if ((adm_ctx->my_addr && nla_len(adm_ctx->my_addr) > sizeof(adm_ctx->connection->my_addr)) || (adm_ctx->peer_addr && @@ -259,7 +227,7 @@ static int drbd_adm_prepare(struct drbd_config_context *adm_ctx, adm_ctx->device = minor_to_device(d_in->minor); /* We are protected by the global genl_lock(). - * But we may explicitly drop it/retake it in drbd_adm_set_role(), + * But we may explicitly drop it/retake it in drbd_nl_set_role(), * so make sure this object stays around. */ if (adm_ctx->device) kref_get(&adm_ctx->device->kref); @@ -334,8 +302,8 @@ fail: return err; } -static int drbd_pre_doit(const struct genl_split_ops *ops, - struct sk_buff *skb, struct genl_info *info) +int drbd_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx; u8 cmd = info->genlhdr->cmd; @@ -362,8 +330,8 @@ static int drbd_pre_doit(const struct genl_split_ops *ops, return 0; } -static void drbd_post_doit(const struct genl_split_ops *ops, - struct sk_buff *skb, struct genl_info *info) +void drbd_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; @@ -828,7 +796,7 @@ static const char *from_attrs_err_to_txt(int err) "invalid attribute value"; } -int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info) +static int drbd_nl_set_role(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct set_role_parms parms; @@ -868,6 +836,16 @@ out: return 0; } +int drbd_nl_primary_doit(struct sk_buff *skb, struct genl_info *info) +{ + return drbd_nl_set_role(skb, info); +} + +int drbd_nl_secondary_doit(struct sk_buff *skb, struct genl_info *info) +{ + return drbd_nl_set_role(skb, info); +} + /* Initializes the md.*_offset members, so we are able to find * the on disk meta data. * @@ -962,7 +940,7 @@ char *ppsize(char *buf, unsigned long long size) * peer may not initiate a resize. */ /* Note these are not to be confused with - * drbd_adm_suspend_io/drbd_adm_resume_io, + * drbd_nl_suspend_io_doit/drbd_nl_resume_io_doit, * which are (sub) state changes triggered by admin (drbdsetup), * and can be long lived. * This changes an device->flag, is triggered by drbd internals, @@ -1574,13 +1552,14 @@ out: return err; } -int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_chg_disk_opts_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; enum drbd_ret_code retcode; struct drbd_device *device; struct disk_conf *new_disk_conf, *old_disk_conf; struct fifo_buffer *old_plan = NULL, *new_plan = NULL; + struct nlattr **ntb; int err; unsigned int fifo_size; @@ -1612,13 +1591,29 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) if (should_set_defaults(info)) set_disk_conf_defaults(new_disk_conf); - err = disk_conf_from_attrs_for_change(new_disk_conf, info); + err = disk_conf_from_attrs(new_disk_conf, info); if (err && err != -ENOMSG) { retcode = ERR_MANDATORY_TAG; drbd_msg_put_info(adm_ctx->reply_skb, from_attrs_err_to_txt(err)); goto fail_unlock; } + err = disk_conf_ntb_from_attrs(&ntb, info); + if (!err) { + if (has_invariant(ntb, DRBD_A_DISK_CONF_BACKING_DEV) || + has_invariant(ntb, DRBD_A_DISK_CONF_META_DEV) || + has_invariant(ntb, DRBD_A_DISK_CONF_META_DEV_IDX) || + has_invariant(ntb, DRBD_A_DISK_CONF_DISK_SIZE) || + has_invariant(ntb, DRBD_A_DISK_CONF_MAX_BIO_BVECS)) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx->reply_skb, + "cannot change invariant setting"); + kfree(ntb); + goto fail_unlock; + } + kfree(ntb); + } + if (!expect(device, new_disk_conf->resync_rate >= 1)) new_disk_conf->resync_rate = 1; @@ -1796,7 +1791,7 @@ void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev * kfree(ldev); } -int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_attach_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct drbd_device *device; @@ -2236,7 +2231,7 @@ static int adm_detach(struct drbd_device *device, int force) * Then we transition to D_DISKLESS, and wait for put_ldev() to return all * internal references as well. * Only then we have finally detached. */ -int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_detach_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; enum drbd_ret_code retcode; @@ -2434,12 +2429,13 @@ static void free_crypto(struct crypto *crypto) crypto_free_shash(crypto->verify_tfm); } -int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_chg_net_opts_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; enum drbd_ret_code retcode; struct drbd_connection *connection; struct net_conf *old_net_conf, *new_net_conf = NULL; + struct nlattr **ntb; int err; int ovr; /* online verify running */ int rsr; /* re-sync running */ @@ -2476,13 +2472,26 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info) if (should_set_defaults(info)) set_net_conf_defaults(new_net_conf); - err = net_conf_from_attrs_for_change(new_net_conf, info); + err = net_conf_from_attrs(new_net_conf, info); if (err && err != -ENOMSG) { retcode = ERR_MANDATORY_TAG; drbd_msg_put_info(adm_ctx->reply_skb, from_attrs_err_to_txt(err)); goto fail; } + err = net_conf_ntb_from_attrs(&ntb, info); + if (!err) { + if (has_invariant(ntb, DRBD_A_NET_CONF_DISCARD_MY_DATA) || + has_invariant(ntb, DRBD_A_NET_CONF_TENTATIVE)) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx->reply_skb, + "cannot change invariant setting"); + kfree(ntb); + goto fail; + } + kfree(ntb); + } + retcode = check_net_options(connection, new_net_conf); if (retcode != NO_ERROR) goto fail; @@ -2575,7 +2584,7 @@ static void peer_device_to_info(struct peer_device_info *info, info->peer_resync_susp_dependency = device->state.aftr_isp; } -int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_connect_doit(struct sk_buff *skb, struct genl_info *info) { struct connection_info connection_info; enum drbd_notification_type flags; @@ -2790,7 +2799,7 @@ repeat: return rv; } -int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_disconnect_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct disconnect_parms parms; @@ -2845,7 +2854,7 @@ void resync_after_online_grow(struct drbd_device *device) _drbd_request_state(device, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE + CS_SERIALIZE); } -int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_resize_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct disk_conf *old_disk_conf, *new_disk_conf = NULL; @@ -2981,7 +2990,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) goto fail; } -int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_resource_opts_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; enum drbd_ret_code retcode; @@ -3019,7 +3028,7 @@ fail: return 0; } -int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_invalidate_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct drbd_device *device; @@ -3097,7 +3106,7 @@ static int drbd_bmio_set_susp_al(struct drbd_device *device, return rv; } -int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_inval_peer_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; int retcode; /* drbd_ret_code, drbd_state_rv */ @@ -3148,7 +3157,7 @@ out: return 0; } -int drbd_adm_pause_sync(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_pause_sync_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; enum drbd_ret_code retcode; @@ -3168,7 +3177,7 @@ out: return 0; } -int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_resume_sync_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; union drbd_dev_state s; @@ -3196,12 +3205,12 @@ out: return 0; } -int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_suspend_io_doit(struct sk_buff *skb, struct genl_info *info) { return drbd_adm_simple_request_state(skb, info, NS(susp, 1)); } -int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_resume_io_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct drbd_device *device; @@ -3257,7 +3266,7 @@ out: return 0; } -int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_outdate_doit(struct sk_buff *skb, struct genl_info *info) { return drbd_adm_simple_request_state(skb, info, NS(disk, D_OUTDATED)); } @@ -3272,16 +3281,20 @@ static int nla_put_drbd_cfg_context(struct sk_buff *skb, if (!nla) goto nla_put_failure; if (device && - nla_put_u32(skb, T_ctx_volume, device->vnr)) + nla_put_u32(skb, DRBD_A_DRBD_CFG_CONTEXT_CTX_VOLUME, device->vnr)) goto nla_put_failure; - if (nla_put_string(skb, T_ctx_resource_name, resource->name)) + if (nla_put_string(skb, DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME, resource->name)) goto nla_put_failure; if (connection) { if (connection->my_addr_len && - nla_put(skb, T_ctx_my_addr, connection->my_addr_len, &connection->my_addr)) + nla_put(skb, DRBD_A_DRBD_CFG_CONTEXT_CTX_MY_ADDR, + connection->my_addr_len, + &connection->my_addr)) goto nla_put_failure; if (connection->peer_addr_len && - nla_put(skb, T_ctx_peer_addr, connection->peer_addr_len, &connection->peer_addr)) + nla_put(skb, DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR, + connection->peer_addr_len, + &connection->peer_addr)) goto nla_put_failure; } nla_nest_end(skb, nla); @@ -3300,7 +3313,7 @@ nla_put_failure: */ static struct nlattr *find_cfg_context_attr(const struct nlmsghdr *nlh, int attr) { - const unsigned hdrlen = GENL_HDRLEN + GENL_MAGIC_FAMILY_HDRSZ; + const unsigned int hdrlen = GENL_HDRLEN + sizeof(struct drbd_genlmsghdr); struct nlattr *nla; nla = nla_find(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), @@ -3312,7 +3325,7 @@ static struct nlattr *find_cfg_context_attr(const struct nlmsghdr *nlh, int attr static void resource_to_info(struct resource_info *, struct drbd_resource *); -int drbd_adm_dump_resources(struct sk_buff *skb, struct netlink_callback *cb) +int drbd_nl_get_resources_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct drbd_genlmsghdr *dh; struct drbd_resource *resource; @@ -3340,7 +3353,7 @@ found_resource: put_result: dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &drbd_genl_family, + cb->nlh->nlmsg_seq, &drbd_nl_family, NLM_F_MULTI, DRBD_ADM_GET_RESOURCES); err = -ENOMEM; if (!dh) @@ -3350,15 +3363,15 @@ put_result: err = nla_put_drbd_cfg_context(skb, resource, NULL, NULL); if (err) goto out; - err = res_opts_to_skb(skb, &resource->res_opts, !capable(CAP_SYS_ADMIN)); + err = res_opts_to_skb(skb, &resource->res_opts); if (err) goto out; resource_to_info(&resource_info, resource); - err = resource_info_to_skb(skb, &resource_info, !capable(CAP_SYS_ADMIN)); + err = resource_info_to_skb(skb, &resource_info); if (err) goto out; resource_statistics.res_stat_write_ordering = resource->write_ordering; - err = resource_statistics_to_skb(skb, &resource_statistics, !capable(CAP_SYS_ADMIN)); + err = resource_statistics_to_skb(skb, &resource_statistics); if (err) goto out; cb->args[0] = (long)resource; @@ -3423,7 +3436,7 @@ int drbd_adm_dump_devices_done(struct netlink_callback *cb) { static void device_to_info(struct device_info *, struct drbd_device *); -int drbd_adm_dump_devices(struct sk_buff *skb, struct netlink_callback *cb) +int drbd_nl_get_devices_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *resource_filter; struct drbd_resource *resource; @@ -3436,7 +3449,8 @@ int drbd_adm_dump_devices(struct sk_buff *skb, struct netlink_callback *cb) resource = (struct drbd_resource *)cb->args[0]; if (!cb->args[0] && !cb->args[1]) { - resource_filter = find_cfg_context_attr(cb->nlh, T_ctx_resource_name); + resource_filter = find_cfg_context_attr(cb->nlh, + DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME); if (resource_filter) { retcode = ERR_RES_NOT_KNOWN; resource = drbd_find_resource(nla_data(resource_filter)); @@ -3465,7 +3479,7 @@ int drbd_adm_dump_devices(struct sk_buff *skb, struct netlink_callback *cb) put_result: dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &drbd_genl_family, + cb->nlh->nlmsg_seq, &drbd_nl_family, NLM_F_MULTI, DRBD_ADM_GET_DEVICES); err = -ENOMEM; if (!dh) @@ -3481,18 +3495,18 @@ put_result: struct disk_conf *disk_conf = rcu_dereference(device->ldev->disk_conf); - err = disk_conf_to_skb(skb, disk_conf, !capable(CAP_SYS_ADMIN)); + err = disk_conf_to_skb(skb, disk_conf); put_ldev(device); if (err) goto out; } device_to_info(&device_info, device); - err = device_info_to_skb(skb, &device_info, !capable(CAP_SYS_ADMIN)); + err = device_info_to_skb(skb, &device_info); if (err) goto out; device_to_statistics(&device_statistics, device); - err = device_statistics_to_skb(skb, &device_statistics, !capable(CAP_SYS_ADMIN)); + err = device_statistics_to_skb(skb, &device_statistics); if (err) goto out; cb->args[1] = minor + 1; @@ -3514,7 +3528,7 @@ int drbd_adm_dump_connections_done(struct netlink_callback *cb) enum { SINGLE_RESOURCE, ITERATE_RESOURCES }; -int drbd_adm_dump_connections(struct sk_buff *skb, struct netlink_callback *cb) +int drbd_nl_get_connections_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *resource_filter; struct drbd_resource *resource = NULL, *next_resource; @@ -3527,7 +3541,8 @@ int drbd_adm_dump_connections(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); resource = (struct drbd_resource *)cb->args[0]; if (!cb->args[0]) { - resource_filter = find_cfg_context_attr(cb->nlh, T_ctx_resource_name); + resource_filter = find_cfg_context_attr(cb->nlh, + DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME); if (resource_filter) { retcode = ERR_RES_NOT_KNOWN; resource = drbd_find_resource(nla_data(resource_filter)); @@ -3591,7 +3606,7 @@ found_resource: put_result: dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &drbd_genl_family, + cb->nlh->nlmsg_seq, &drbd_nl_family, NLM_F_MULTI, DRBD_ADM_GET_CONNECTIONS); err = -ENOMEM; if (!dh) @@ -3606,16 +3621,16 @@ put_result: goto out; net_conf = rcu_dereference(connection->net_conf); if (net_conf) { - err = net_conf_to_skb(skb, net_conf, !capable(CAP_SYS_ADMIN)); + err = net_conf_to_skb(skb, net_conf); if (err) goto out; } connection_to_info(&connection_info, connection); - err = connection_info_to_skb(skb, &connection_info, !capable(CAP_SYS_ADMIN)); + err = connection_info_to_skb(skb, &connection_info); if (err) goto out; connection_statistics.conn_congested = test_bit(NET_CONGESTED, &connection->flags); - err = connection_statistics_to_skb(skb, &connection_statistics, !capable(CAP_SYS_ADMIN)); + err = connection_statistics_to_skb(skb, &connection_statistics); if (err) goto out; cb->args[2] = (long)connection; @@ -3676,7 +3691,7 @@ int drbd_adm_dump_peer_devices_done(struct netlink_callback *cb) return put_resource_in_arg0(cb, 9); } -int drbd_adm_dump_peer_devices(struct sk_buff *skb, struct netlink_callback *cb) +int drbd_nl_get_peer_devices_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *resource_filter; struct drbd_resource *resource; @@ -3688,7 +3703,8 @@ int drbd_adm_dump_peer_devices(struct sk_buff *skb, struct netlink_callback *cb) resource = (struct drbd_resource *)cb->args[0]; if (!cb->args[0] && !cb->args[1]) { - resource_filter = find_cfg_context_attr(cb->nlh, T_ctx_resource_name); + resource_filter = find_cfg_context_attr(cb->nlh, + DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME); if (resource_filter) { retcode = ERR_RES_NOT_KNOWN; resource = drbd_find_resource(nla_data(resource_filter)); @@ -3735,7 +3751,7 @@ found_peer_device: put_result: dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &drbd_genl_family, + cb->nlh->nlmsg_seq, &drbd_nl_family, NLM_F_MULTI, DRBD_ADM_GET_PEER_DEVICES); err = -ENOMEM; if (!dh) @@ -3751,11 +3767,11 @@ put_result: if (err) goto out; peer_device_to_info(&peer_device_info, peer_device); - err = peer_device_info_to_skb(skb, &peer_device_info, !capable(CAP_SYS_ADMIN)); + err = peer_device_info_to_skb(skb, &peer_device_info); if (err) goto out; peer_device_to_statistics(&peer_device_statistics, peer_device); - err = peer_device_statistics_to_skb(skb, &peer_device_statistics, !capable(CAP_SYS_ADMIN)); + err = peer_device_statistics_to_skb(skb, &peer_device_statistics); if (err) goto out; cb->args[1] = minor; @@ -3795,11 +3811,11 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device, /* If sib != NULL, this is drbd_bcast_event, which anyone can listen * to. So we better exclude_sensitive information. * - * If sib == NULL, this is drbd_adm_get_status, executed synchronously + * If sib == NULL, this is drbd_nl_get_status_doit, executed synchronously * in the context of the requesting user process. Exclude sensitive * information, unless current has superuser. * - * NOTE: for drbd_adm_get_status_all(), this is a netlink dump, and + * NOTE: for drbd_nl_get_status_dumpit(), this is a netlink dump, and * relies on the current implementation of netlink_dump(), which * executes the dump callback successively from netlink_recvmsg(), * always in the context of the receiving process */ @@ -3812,7 +3828,7 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device, if (nla_put_drbd_cfg_context(skb, resource, the_only_connection(resource), device)) goto nla_put_failure; - if (res_opts_to_skb(skb, &device->resource->res_opts, exclude_sensitive)) + if (res_opts_to_skb(skb, &device->resource->res_opts)) goto nla_put_failure; rcu_read_lock(); @@ -3820,14 +3836,24 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device, struct disk_conf *disk_conf; disk_conf = rcu_dereference(device->ldev->disk_conf); - err = disk_conf_to_skb(skb, disk_conf, exclude_sensitive); + err = disk_conf_to_skb(skb, disk_conf); } if (!err) { struct net_conf *nc; nc = rcu_dereference(first_peer_device(device)->connection->net_conf); - if (nc) - err = net_conf_to_skb(skb, nc, exclude_sensitive); + if (nc) { + if (exclude_sensitive) { + struct net_conf nc_clean = *nc; + + memset(nc_clean.shared_secret, 0, + sizeof(nc_clean.shared_secret)); + nc_clean.shared_secret_len = 0; + err = net_conf_to_skb(skb, &nc_clean); + } else { + err = net_conf_to_skb(skb, nc); + } + } } rcu_read_unlock(); if (err) @@ -3836,42 +3862,57 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device, nla = nla_nest_start_noflag(skb, DRBD_NLA_STATE_INFO); if (!nla) goto nla_put_failure; - if (nla_put_u32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY) || - nla_put_u32(skb, T_current_state, device->state.i) || - nla_put_u64_0pad(skb, T_ed_uuid, device->ed_uuid) || - nla_put_u64_0pad(skb, T_capacity, get_capacity(device->vdisk)) || - nla_put_u64_0pad(skb, T_send_cnt, device->send_cnt) || - nla_put_u64_0pad(skb, T_recv_cnt, device->recv_cnt) || - nla_put_u64_0pad(skb, T_read_cnt, device->read_cnt) || - nla_put_u64_0pad(skb, T_writ_cnt, device->writ_cnt) || - nla_put_u64_0pad(skb, T_al_writ_cnt, device->al_writ_cnt) || - nla_put_u64_0pad(skb, T_bm_writ_cnt, device->bm_writ_cnt) || - nla_put_u32(skb, T_ap_bio_cnt, atomic_read(&device->ap_bio_cnt)) || - nla_put_u32(skb, T_ap_pending_cnt, atomic_read(&device->ap_pending_cnt)) || - nla_put_u32(skb, T_rs_pending_cnt, atomic_read(&device->rs_pending_cnt))) + if (nla_put_u32(skb, DRBD_A_STATE_INFO_SIB_REASON, + sib ? sib->sib_reason : SIB_GET_STATUS_REPLY) || + nla_put_u32(skb, DRBD_A_STATE_INFO_CURRENT_STATE, + device->state.i) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_ED_UUID, + device->ed_uuid, 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_CAPACITY, + get_capacity(device->vdisk), 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_SEND_CNT, + device->send_cnt, 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_RECV_CNT, + device->recv_cnt, 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_READ_CNT, + device->read_cnt, 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_WRIT_CNT, + device->writ_cnt, 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_AL_WRIT_CNT, + device->al_writ_cnt, 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BM_WRIT_CNT, + device->bm_writ_cnt, 0) || + nla_put_u32(skb, DRBD_A_STATE_INFO_AP_BIO_CNT, + atomic_read(&device->ap_bio_cnt)) || + nla_put_u32(skb, DRBD_A_STATE_INFO_AP_PENDING_CNT, + atomic_read(&device->ap_pending_cnt)) || + nla_put_u32(skb, DRBD_A_STATE_INFO_RS_PENDING_CNT, + atomic_read(&device->rs_pending_cnt))) goto nla_put_failure; if (got_ldev) { int err; spin_lock_irq(&device->ldev->md.uuid_lock); - err = nla_put(skb, T_uuids, sizeof(si->uuids), device->ldev->md.uuid); + err = nla_put(skb, DRBD_A_STATE_INFO_UUIDS, + sizeof(si->uuids), + device->ldev->md.uuid); spin_unlock_irq(&device->ldev->md.uuid_lock); if (err) goto nla_put_failure; - if (nla_put_u32(skb, T_disk_flags, device->ldev->md.flags) || - nla_put_u64_0pad(skb, T_bits_total, drbd_bm_bits(device)) || - nla_put_u64_0pad(skb, T_bits_oos, - drbd_bm_total_weight(device))) + if (nla_put_u32(skb, DRBD_A_STATE_INFO_DISK_FLAGS, device->ldev->md.flags) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BITS_TOTAL, drbd_bm_bits(device), 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BITS_OOS, + drbd_bm_total_weight(device), 0)) goto nla_put_failure; if (C_SYNC_SOURCE <= device->state.conn && C_PAUSED_SYNC_T >= device->state.conn) { - if (nla_put_u64_0pad(skb, T_bits_rs_total, - device->rs_total) || - nla_put_u64_0pad(skb, T_bits_rs_failed, - device->rs_failed)) + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BITS_RS_TOTAL, + device->rs_total, 0) || + nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BITS_RS_FAILED, + device->rs_failed, 0)) goto nla_put_failure; } } @@ -3882,17 +3923,17 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device, case SIB_GET_STATUS_REPLY: break; case SIB_STATE_CHANGE: - if (nla_put_u32(skb, T_prev_state, sib->os.i) || - nla_put_u32(skb, T_new_state, sib->ns.i)) + if (nla_put_u32(skb, DRBD_A_STATE_INFO_PREV_STATE, sib->os.i) || + nla_put_u32(skb, DRBD_A_STATE_INFO_NEW_STATE, sib->ns.i)) goto nla_put_failure; break; case SIB_HELPER_POST: - if (nla_put_u32(skb, T_helper_exit_code, + if (nla_put_u32(skb, DRBD_A_STATE_INFO_HELPER_EXIT_CODE, sib->helper_exit_code)) goto nla_put_failure; fallthrough; case SIB_HELPER_PRE: - if (nla_put_string(skb, T_helper, sib->helper_name)) + if (nla_put_string(skb, DRBD_A_STATE_INFO_HELPER, sib->helper_name)) goto nla_put_failure; break; } @@ -3907,7 +3948,7 @@ nla_put_failure: return err; } -int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_get_status_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; enum drbd_ret_code retcode; @@ -3997,7 +4038,7 @@ next_resource: } dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &drbd_genl_family, + cb->nlh->nlmsg_seq, &drbd_nl_family, NLM_F_MULTI, DRBD_ADM_GET_STATUS); if (!dh) goto out; @@ -4017,7 +4058,7 @@ next_resource: struct net_conf *nc; nc = rcu_dereference(connection->net_conf); - if (nc && net_conf_to_skb(skb, nc, 1) != 0) + if (nc && net_conf_to_skb(skb, nc) != 0) goto cancel; } goto done; @@ -4059,9 +4100,9 @@ out: * * Once things are setup properly, we call into get_one_status(). */ -int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb) +int drbd_nl_get_status_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - const unsigned hdrlen = GENL_HDRLEN + GENL_MAGIC_FAMILY_HDRSZ; + const unsigned int hdrlen = GENL_HDRLEN + sizeof(struct drbd_genlmsghdr); struct nlattr *nla; const char *resource_name; struct drbd_resource *resource; @@ -4084,7 +4125,7 @@ int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb) /* No explicit context given. Dump all. */ if (!nla) goto dump; - nla = nla_find_nested(nla, T_ctx_resource_name); + nla = nla_find_nested(nla, DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME); /* context given, but no name present? */ if (!nla) return -EINVAL; @@ -4107,7 +4148,7 @@ dump: return get_one_status(skb, cb); } -int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_get_timeout_type_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; enum drbd_ret_code retcode; @@ -4125,7 +4166,7 @@ int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info) test_bit(USE_DEGR_WFC_T, &adm_ctx->device->flags) ? UT_DEGRADED : UT_DEFAULT; - err = timeout_parms_to_priv_skb(adm_ctx->reply_skb, &tp); + err = timeout_parms_to_skb(adm_ctx->reply_skb, &tp); if (err) { nlmsg_free(adm_ctx->reply_skb); adm_ctx->reply_skb = NULL; @@ -4136,7 +4177,7 @@ out: return 0; } -int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_start_ov_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct drbd_device *device; @@ -4182,7 +4223,7 @@ out: } -int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_new_c_uuid_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct drbd_device *device; @@ -4285,7 +4326,7 @@ static void resource_to_info(struct resource_info *info, info->res_susp_fen = resource->susp_fen; } -int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_new_resource_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_connection *connection; struct drbd_config_context *adm_ctx = info->user_ptr[0]; @@ -4348,7 +4389,7 @@ static void device_to_info(struct device_info *info, } -int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_new_minor_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct drbd_genlmsghdr *dh = genl_info_userhdr(info); @@ -4455,7 +4496,7 @@ static enum drbd_ret_code adm_del_minor(struct drbd_device *device) return ERR_MINOR_CONFIGURED; } -int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_del_minor_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; enum drbd_ret_code retcode; @@ -4504,7 +4545,7 @@ static int adm_del_resource(struct drbd_resource *resource) return NO_ERROR; } -int drbd_adm_down(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_down_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct drbd_resource *resource; @@ -4567,7 +4608,7 @@ finish: return 0; } -int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info) +int drbd_nl_del_resource_doit(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context *adm_ctx = info->user_ptr[0]; struct drbd_resource *resource; @@ -4601,7 +4642,7 @@ void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib) goto failed; err = -EMSGSIZE; - d_out = genlmsg_put(msg, 0, seq, &drbd_genl_family, 0, DRBD_EVENT); + d_out = genlmsg_put(msg, 0, seq, &drbd_nl_family, 0, DRBD_ADM_EVENT); if (!d_out) /* cannot happen, but anyways. */ goto nla_put_failure; d_out->minor = device_to_minor(device); @@ -4632,7 +4673,7 @@ static int nla_put_notification_header(struct sk_buff *msg, .nh_type = type, }; - return drbd_notification_header_to_skb(msg, &nh, true); + return drbd_notification_header_to_skb(msg, &nh); } int notify_resource_state(struct sk_buff *skb, @@ -4656,7 +4697,7 @@ int notify_resource_state(struct sk_buff *skb, } err = -EMSGSIZE; - dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_RESOURCE_STATE); + dh = genlmsg_put(skb, 0, seq, &drbd_nl_family, 0, DRBD_ADM_RESOURCE_STATE); if (!dh) goto nla_put_failure; dh->minor = -1U; @@ -4664,10 +4705,10 @@ int notify_resource_state(struct sk_buff *skb, if (nla_put_drbd_cfg_context(skb, resource, NULL, NULL) || nla_put_notification_header(skb, type) || ((type & ~NOTIFY_FLAGS) != NOTIFY_DESTROY && - resource_info_to_skb(skb, resource_info, true))) + resource_info_to_skb(skb, resource_info))) goto nla_put_failure; resource_statistics.res_stat_write_ordering = resource->write_ordering; - err = resource_statistics_to_skb(skb, &resource_statistics, !capable(CAP_SYS_ADMIN)); + err = resource_statistics_to_skb(skb, &resource_statistics); if (err) goto nla_put_failure; genlmsg_end(skb, dh); @@ -4708,7 +4749,7 @@ int notify_device_state(struct sk_buff *skb, } err = -EMSGSIZE; - dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_DEVICE_STATE); + dh = genlmsg_put(skb, 0, seq, &drbd_nl_family, 0, DRBD_ADM_DEVICE_STATE); if (!dh) goto nla_put_failure; dh->minor = device->minor; @@ -4716,10 +4757,10 @@ int notify_device_state(struct sk_buff *skb, if (nla_put_drbd_cfg_context(skb, device->resource, NULL, device) || nla_put_notification_header(skb, type) || ((type & ~NOTIFY_FLAGS) != NOTIFY_DESTROY && - device_info_to_skb(skb, device_info, true))) + device_info_to_skb(skb, device_info))) goto nla_put_failure; device_to_statistics(&device_statistics, device); - device_statistics_to_skb(skb, &device_statistics, !capable(CAP_SYS_ADMIN)); + device_statistics_to_skb(skb, &device_statistics); genlmsg_end(skb, dh); if (multicast) { err = drbd_genl_multicast_events(skb, GFP_NOWAIT); @@ -4758,7 +4799,7 @@ int notify_connection_state(struct sk_buff *skb, } err = -EMSGSIZE; - dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_CONNECTION_STATE); + dh = genlmsg_put(skb, 0, seq, &drbd_nl_family, 0, DRBD_ADM_CONNECTION_STATE); if (!dh) goto nla_put_failure; dh->minor = -1U; @@ -4766,10 +4807,10 @@ int notify_connection_state(struct sk_buff *skb, if (nla_put_drbd_cfg_context(skb, connection->resource, connection, NULL) || nla_put_notification_header(skb, type) || ((type & ~NOTIFY_FLAGS) != NOTIFY_DESTROY && - connection_info_to_skb(skb, connection_info, true))) + connection_info_to_skb(skb, connection_info))) goto nla_put_failure; connection_statistics.conn_congested = test_bit(NET_CONGESTED, &connection->flags); - connection_statistics_to_skb(skb, &connection_statistics, !capable(CAP_SYS_ADMIN)); + connection_statistics_to_skb(skb, &connection_statistics); genlmsg_end(skb, dh); if (multicast) { err = drbd_genl_multicast_events(skb, GFP_NOWAIT); @@ -4809,7 +4850,7 @@ int notify_peer_device_state(struct sk_buff *skb, } err = -EMSGSIZE; - dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_PEER_DEVICE_STATE); + dh = genlmsg_put(skb, 0, seq, &drbd_nl_family, 0, DRBD_ADM_PEER_DEVICE_STATE); if (!dh) goto nla_put_failure; dh->minor = -1U; @@ -4817,10 +4858,10 @@ int notify_peer_device_state(struct sk_buff *skb, if (nla_put_drbd_cfg_context(skb, resource, peer_device->connection, peer_device->device) || nla_put_notification_header(skb, type) || ((type & ~NOTIFY_FLAGS) != NOTIFY_DESTROY && - peer_device_info_to_skb(skb, peer_device_info, true))) + peer_device_info_to_skb(skb, peer_device_info))) goto nla_put_failure; peer_device_to_statistics(&peer_device_statistics, peer_device); - peer_device_statistics_to_skb(skb, &peer_device_statistics, !capable(CAP_SYS_ADMIN)); + peer_device_statistics_to_skb(skb, &peer_device_statistics); genlmsg_end(skb, dh); if (multicast) { err = drbd_genl_multicast_events(skb, GFP_NOWAIT); @@ -4859,7 +4900,7 @@ void notify_helper(enum drbd_notification_type type, goto fail; err = -EMSGSIZE; - dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_HELPER); + dh = genlmsg_put(skb, 0, seq, &drbd_nl_family, 0, DRBD_ADM_HELPER); if (!dh) goto fail; dh->minor = device ? device->minor : -1; @@ -4867,7 +4908,7 @@ void notify_helper(enum drbd_notification_type type, mutex_lock(¬ification_mutex); if (nla_put_drbd_cfg_context(skb, resource, connection, device) || nla_put_notification_header(skb, type) || - drbd_helper_info_to_skb(skb, &helper_info, true)) + drbd_helper_info_to_skb(skb, &helper_info)) goto unlock_fail; genlmsg_end(skb, dh); err = drbd_genl_multicast_events(skb, GFP_NOWAIT); @@ -4892,7 +4933,7 @@ static int notify_initial_state_done(struct sk_buff *skb, unsigned int seq) int err; err = -EMSGSIZE; - dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_INITIAL_STATE_DONE); + dh = genlmsg_put(skb, 0, seq, &drbd_nl_family, 0, DRBD_ADM_INITIAL_STATE_DONE); if (!dh) goto nla_put_failure; dh->minor = -1U; @@ -4987,7 +5028,7 @@ out: return skb->len; } -int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) +int drbd_nl_get_initial_state_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct drbd_resource *resource; LIST_HEAD(head); @@ -5035,3 +5076,20 @@ int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) cb->args[2] = cb->nlh->nlmsg_seq; return get_initial_state(skb, cb); } + +static const struct genl_multicast_group drbd_nl_mcgrps[] = { + [DRBD_NLGRP_EVENTS] = { .name = "events", }, +}; + +struct genl_family drbd_nl_family __ro_after_init = { + .name = "drbd", + .version = DRBD_FAMILY_VERSION, + .hdrsize = NLA_ALIGN(sizeof(struct drbd_genlmsghdr)), + .split_ops = drbd_nl_ops, + .n_split_ops = ARRAY_SIZE(drbd_nl_ops), + .mcgrps = drbd_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(drbd_nl_mcgrps), + .resv_start_op = 42, + .module = THIS_MODULE, + .netnsok = true, +}; diff --git a/drivers/block/drbd/drbd_nl_gen.c b/drivers/block/drbd/drbd_nl_gen.c new file mode 100644 index 000000000000..fb44b948cec8 --- /dev/null +++ b/drivers/block/drbd/drbd_nl_gen.c @@ -0,0 +1,2606 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +#include +#include + +#include +#include +#include "drbd_nl_gen.h" + +#include +#include +#include + +/* Common nested types */ +const struct nla_policy drbd_connection_info_nl_policy[DRBD_A_CONNECTION_INFO_CONN_ROLE + 1] = { + [DRBD_A_CONNECTION_INFO_CONN_CONNECTION_STATE] = { .type = NLA_U32, }, + [DRBD_A_CONNECTION_INFO_CONN_ROLE] = { .type = NLA_U32, }, +}; + +const struct nla_policy drbd_connection_statistics_nl_policy[DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED + 1] = { + [DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED] = { .type = NLA_U8, }, +}; + +const struct nla_policy drbd_detach_parms_nl_policy[DRBD_A_DETACH_PARMS_FORCE_DETACH + 1] = { + [DRBD_A_DETACH_PARMS_FORCE_DETACH] = { .type = NLA_U8, }, +}; + +const struct nla_policy drbd_device_info_nl_policy[DRBD_A_DEVICE_INFO_DEV_DISK_STATE + 1] = { + [DRBD_A_DEVICE_INFO_DEV_DISK_STATE] = { .type = NLA_U32, }, +}; + +const struct nla_policy drbd_device_statistics_nl_policy[DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS + 1] = { + [DRBD_A_DEVICE_STATISTICS_DEV_SIZE] = { .type = NLA_U64, }, + [DRBD_A_DEVICE_STATISTICS_DEV_READ] = { .type = NLA_U64, }, + [DRBD_A_DEVICE_STATISTICS_DEV_WRITE] = { .type = NLA_U64, }, + [DRBD_A_DEVICE_STATISTICS_DEV_AL_WRITES] = { .type = NLA_U64, }, + [DRBD_A_DEVICE_STATISTICS_DEV_BM_WRITES] = { .type = NLA_U64, }, + [DRBD_A_DEVICE_STATISTICS_DEV_UPPER_PENDING] = { .type = NLA_U32, }, + [DRBD_A_DEVICE_STATISTICS_DEV_LOWER_PENDING] = { .type = NLA_U32, }, + [DRBD_A_DEVICE_STATISTICS_DEV_UPPER_BLOCKED] = { .type = NLA_U8, }, + [DRBD_A_DEVICE_STATISTICS_DEV_LOWER_BLOCKED] = { .type = NLA_U8, }, + [DRBD_A_DEVICE_STATISTICS_DEV_AL_SUSPENDED] = { .type = NLA_U8, }, + [DRBD_A_DEVICE_STATISTICS_DEV_EXPOSED_DATA_UUID] = { .type = NLA_U64, }, + [DRBD_A_DEVICE_STATISTICS_DEV_CURRENT_UUID] = { .type = NLA_U64, }, + [DRBD_A_DEVICE_STATISTICS_DEV_DISK_FLAGS] = { .type = NLA_U32, }, + [DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS] = NLA_POLICY_MAX_LEN(DRBD_NL_HISTORY_UUIDS_SIZE), +}; + +const struct nla_policy drbd_disconnect_parms_nl_policy[DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT + 1] = { + [DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT] = { .type = NLA_U8, }, +}; + +const struct nla_policy drbd_disk_conf_nl_policy[DRBD_A_DISK_CONF_DISABLE_WRITE_SAME + 1] = { + [DRBD_A_DISK_CONF_BACKING_DEV] = { .type = NLA_NUL_STRING, .len = 128, }, + [DRBD_A_DISK_CONF_META_DEV] = { .type = NLA_NUL_STRING, .len = 128, }, + [DRBD_A_DISK_CONF_META_DEV_IDX] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_DISK_SIZE] = { .type = NLA_U64, }, + [DRBD_A_DISK_CONF_MAX_BIO_BVECS] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_ON_IO_ERROR] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_FENCING] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_RESYNC_RATE] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_RESYNC_AFTER] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_AL_EXTENTS] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_C_PLAN_AHEAD] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_C_DELAY_TARGET] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_C_FILL_TARGET] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_C_MAX_RATE] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_C_MIN_RATE] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_DISK_BARRIER] = { .type = NLA_U8, }, + [DRBD_A_DISK_CONF_DISK_FLUSHES] = { .type = NLA_U8, }, + [DRBD_A_DISK_CONF_DISK_DRAIN] = { .type = NLA_U8, }, + [DRBD_A_DISK_CONF_MD_FLUSHES] = { .type = NLA_U8, }, + [DRBD_A_DISK_CONF_DISK_TIMEOUT] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_READ_BALANCING] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_AL_UPDATES] = { .type = NLA_U8, }, + [DRBD_A_DISK_CONF_DISCARD_ZEROES_IF_ALIGNED] = { .type = NLA_U8, }, + [DRBD_A_DISK_CONF_RS_DISCARD_GRANULARITY] = { .type = NLA_U32, }, + [DRBD_A_DISK_CONF_DISABLE_WRITE_SAME] = { .type = NLA_U8, }, +}; + +const struct nla_policy drbd_drbd_cfg_context_nl_policy[DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR + 1] = { + [DRBD_A_DRBD_CFG_CONTEXT_CTX_VOLUME] = { .type = NLA_U32, }, + [DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME] = { .type = NLA_NUL_STRING, .len = 128, }, + [DRBD_A_DRBD_CFG_CONTEXT_CTX_MY_ADDR] = NLA_POLICY_MAX_LEN(128), + [DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR] = NLA_POLICY_MAX_LEN(128), +}; + +const struct nla_policy drbd_net_conf_nl_policy[DRBD_A_NET_CONF_SOCK_CHECK_TIMEO + 1] = { + [DRBD_A_NET_CONF_SHARED_SECRET] = { .type = NLA_NUL_STRING, .len = SHARED_SECRET_MAX, }, + [DRBD_A_NET_CONF_CRAM_HMAC_ALG] = { .type = NLA_NUL_STRING, .len = SHARED_SECRET_MAX, }, + [DRBD_A_NET_CONF_INTEGRITY_ALG] = { .type = NLA_NUL_STRING, .len = SHARED_SECRET_MAX, }, + [DRBD_A_NET_CONF_VERIFY_ALG] = { .type = NLA_NUL_STRING, .len = SHARED_SECRET_MAX, }, + [DRBD_A_NET_CONF_CSUMS_ALG] = { .type = NLA_NUL_STRING, .len = SHARED_SECRET_MAX, }, + [DRBD_A_NET_CONF_WIRE_PROTOCOL] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_CONNECT_INT] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_TIMEOUT] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_PING_INT] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_PING_TIMEO] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_SNDBUF_SIZE] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_RCVBUF_SIZE] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_KO_COUNT] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_MAX_BUFFERS] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_MAX_EPOCH_SIZE] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_UNPLUG_WATERMARK] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_AFTER_SB_0P] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_AFTER_SB_1P] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_AFTER_SB_2P] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_RR_CONFLICT] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_ON_CONGESTION] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_CONG_FILL] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_CONG_EXTENTS] = { .type = NLA_U32, }, + [DRBD_A_NET_CONF_TWO_PRIMARIES] = { .type = NLA_U8, }, + [DRBD_A_NET_CONF_DISCARD_MY_DATA] = { .type = NLA_U8, }, + [DRBD_A_NET_CONF_TCP_CORK] = { .type = NLA_U8, }, + [DRBD_A_NET_CONF_ALWAYS_ASBP] = { .type = NLA_U8, }, + [DRBD_A_NET_CONF_TENTATIVE] = { .type = NLA_U8, }, + [DRBD_A_NET_CONF_USE_RLE] = { .type = NLA_U8, }, + [DRBD_A_NET_CONF_CSUMS_AFTER_CRASH_ONLY] = { .type = NLA_U8, }, + [DRBD_A_NET_CONF_SOCK_CHECK_TIMEO] = { .type = NLA_U32, }, +}; + +const struct nla_policy drbd_new_c_uuid_parms_nl_policy[DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM + 1] = { + [DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM] = { .type = NLA_U8, }, +}; + +const struct nla_policy drbd_peer_device_info_nl_policy[DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY + 1] = { + [DRBD_A_PEER_DEVICE_INFO_PEER_REPL_STATE] = { .type = NLA_U32, }, + [DRBD_A_PEER_DEVICE_INFO_PEER_DISK_STATE] = { .type = NLA_U32, }, + [DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_USER] = { .type = NLA_U32, }, + [DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_PEER] = { .type = NLA_U32, }, + [DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY] = { .type = NLA_U32, }, +}; + +const struct nla_policy drbd_peer_device_statistics_nl_policy[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS + 1] = { + [DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_RECEIVED] = { .type = NLA_U64, }, + [DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_SENT] = { .type = NLA_U64, }, + [DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_PENDING] = { .type = NLA_U32, }, + [DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_UNACKED] = { .type = NLA_U32, }, + [DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_OUT_OF_SYNC] = { .type = NLA_U64, }, + [DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_RESYNC_FAILED] = { .type = NLA_U64, }, + [DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_BITMAP_UUID] = { .type = NLA_U64, }, + [DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS] = { .type = NLA_U32, }, +}; + +const struct nla_policy drbd_res_opts_nl_policy[DRBD_A_RES_OPTS_ON_NO_DATA + 1] = { + [DRBD_A_RES_OPTS_CPU_MASK] = { .type = NLA_NUL_STRING, .len = DRBD_CPU_MASK_SIZE, }, + [DRBD_A_RES_OPTS_ON_NO_DATA] = { .type = NLA_U32, }, +}; + +const struct nla_policy drbd_resize_parms_nl_policy[DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE + 1] = { + [DRBD_A_RESIZE_PARMS_RESIZE_SIZE] = { .type = NLA_U64, }, + [DRBD_A_RESIZE_PARMS_RESIZE_FORCE] = { .type = NLA_U8, }, + [DRBD_A_RESIZE_PARMS_NO_RESYNC] = { .type = NLA_U8, }, + [DRBD_A_RESIZE_PARMS_AL_STRIPES] = { .type = NLA_U32, }, + [DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE] = { .type = NLA_U32, }, +}; + +const struct nla_policy drbd_resource_info_nl_policy[DRBD_A_RESOURCE_INFO_RES_SUSP_FEN + 1] = { + [DRBD_A_RESOURCE_INFO_RES_ROLE] = { .type = NLA_U32, }, + [DRBD_A_RESOURCE_INFO_RES_SUSP] = { .type = NLA_U8, }, + [DRBD_A_RESOURCE_INFO_RES_SUSP_NOD] = { .type = NLA_U8, }, + [DRBD_A_RESOURCE_INFO_RES_SUSP_FEN] = { .type = NLA_U8, }, +}; + +const struct nla_policy drbd_resource_statistics_nl_policy[DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING + 1] = { + [DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING] = { .type = NLA_U32, }, +}; + +const struct nla_policy drbd_set_role_parms_nl_policy[DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE + 1] = { + [DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE] = { .type = NLA_U8, }, +}; + +const struct nla_policy drbd_start_ov_parms_nl_policy[DRBD_A_START_OV_PARMS_OV_STOP_SECTOR + 1] = { + [DRBD_A_START_OV_PARMS_OV_START_SECTOR] = { .type = NLA_U64, }, + [DRBD_A_START_OV_PARMS_OV_STOP_SECTOR] = { .type = NLA_U64, }, +}; + +/* DRBD_ADM_GET_STATUS - do */ +static const struct nla_policy drbd_get_status_do_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_GET_STATUS - dump */ +static const struct nla_policy drbd_get_status_dump_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_NEW_MINOR - do */ +static const struct nla_policy drbd_new_minor_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_DEL_MINOR - do */ +static const struct nla_policy drbd_del_minor_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_NEW_RESOURCE - do */ +static const struct nla_policy drbd_new_resource_nl_policy[DRBD_NLA_RESOURCE_OPTS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_RESOURCE_OPTS] = NLA_POLICY_NESTED(drbd_res_opts_nl_policy), +}; + +/* DRBD_ADM_DEL_RESOURCE - do */ +static const struct nla_policy drbd_del_resource_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_RESOURCE_OPTS - do */ +static const struct nla_policy drbd_resource_opts_nl_policy[DRBD_NLA_RESOURCE_OPTS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_RESOURCE_OPTS] = NLA_POLICY_NESTED(drbd_res_opts_nl_policy), +}; + +/* DRBD_ADM_CONNECT - do */ +static const struct nla_policy drbd_connect_nl_policy[DRBD_NLA_NET_CONF + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_NET_CONF] = NLA_POLICY_NESTED(drbd_net_conf_nl_policy), +}; + +/* DRBD_ADM_DISCONNECT - do */ +static const struct nla_policy drbd_disconnect_nl_policy[DRBD_NLA_DISCONNECT_PARMS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_DISCONNECT_PARMS] = NLA_POLICY_NESTED(drbd_disconnect_parms_nl_policy), +}; + +/* DRBD_ADM_ATTACH - do */ +static const struct nla_policy drbd_attach_nl_policy[DRBD_NLA_DISK_CONF + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_DISK_CONF] = NLA_POLICY_NESTED(drbd_disk_conf_nl_policy), +}; + +/* DRBD_ADM_RESIZE - do */ +static const struct nla_policy drbd_resize_nl_policy[DRBD_NLA_RESIZE_PARMS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_RESIZE_PARMS] = NLA_POLICY_NESTED(drbd_resize_parms_nl_policy), +}; + +/* DRBD_ADM_PRIMARY - do */ +static const struct nla_policy drbd_primary_nl_policy[DRBD_NLA_SET_ROLE_PARMS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_SET_ROLE_PARMS] = NLA_POLICY_NESTED(drbd_set_role_parms_nl_policy), +}; + +/* DRBD_ADM_SECONDARY - do */ +static const struct nla_policy drbd_secondary_nl_policy[DRBD_NLA_SET_ROLE_PARMS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_SET_ROLE_PARMS] = NLA_POLICY_NESTED(drbd_set_role_parms_nl_policy), +}; + +/* DRBD_ADM_NEW_C_UUID - do */ +static const struct nla_policy drbd_new_c_uuid_nl_policy[DRBD_NLA_NEW_C_UUID_PARMS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_NEW_C_UUID_PARMS] = NLA_POLICY_NESTED(drbd_new_c_uuid_parms_nl_policy), +}; + +/* DRBD_ADM_START_OV - do */ +static const struct nla_policy drbd_start_ov_nl_policy[DRBD_NLA_START_OV_PARMS + 1] = { + [DRBD_NLA_START_OV_PARMS] = NLA_POLICY_NESTED(drbd_start_ov_parms_nl_policy), +}; + +/* DRBD_ADM_DETACH - do */ +static const struct nla_policy drbd_detach_nl_policy[DRBD_NLA_DETACH_PARMS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_DETACH_PARMS] = NLA_POLICY_NESTED(drbd_detach_parms_nl_policy), +}; + +/* DRBD_ADM_INVALIDATE - do */ +static const struct nla_policy drbd_invalidate_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_INVAL_PEER - do */ +static const struct nla_policy drbd_inval_peer_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_PAUSE_SYNC - do */ +static const struct nla_policy drbd_pause_sync_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_RESUME_SYNC - do */ +static const struct nla_policy drbd_resume_sync_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_SUSPEND_IO - do */ +static const struct nla_policy drbd_suspend_io_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_RESUME_IO - do */ +static const struct nla_policy drbd_resume_io_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_OUTDATE - do */ +static const struct nla_policy drbd_outdate_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_GET_TIMEOUT_TYPE - do */ +static const struct nla_policy drbd_get_timeout_type_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_DOWN - do */ +static const struct nla_policy drbd_down_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* DRBD_ADM_CHG_DISK_OPTS - do */ +static const struct nla_policy drbd_chg_disk_opts_nl_policy[DRBD_NLA_DISK_CONF + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_DISK_CONF] = NLA_POLICY_NESTED(drbd_disk_conf_nl_policy), +}; + +/* DRBD_ADM_CHG_NET_OPTS - do */ +static const struct nla_policy drbd_chg_net_opts_nl_policy[DRBD_NLA_NET_CONF + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_NET_CONF] = NLA_POLICY_NESTED(drbd_net_conf_nl_policy), +}; + +/* DRBD_ADM_GET_RESOURCES - dump */ +static const struct nla_policy drbd_get_resources_nl_policy[DRBD_NLA_RESOURCE_STATISTICS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_RESOURCE_INFO] = NLA_POLICY_NESTED(drbd_resource_info_nl_policy), + [DRBD_NLA_RESOURCE_STATISTICS] = NLA_POLICY_NESTED(drbd_resource_statistics_nl_policy), +}; + +/* DRBD_ADM_GET_DEVICES - dump */ +static const struct nla_policy drbd_get_devices_nl_policy[DRBD_NLA_DEVICE_STATISTICS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_DEVICE_INFO] = NLA_POLICY_NESTED(drbd_device_info_nl_policy), + [DRBD_NLA_DEVICE_STATISTICS] = NLA_POLICY_NESTED(drbd_device_statistics_nl_policy), +}; + +/* DRBD_ADM_GET_CONNECTIONS - dump */ +static const struct nla_policy drbd_get_connections_nl_policy[DRBD_NLA_CONNECTION_STATISTICS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_CONNECTION_INFO] = NLA_POLICY_NESTED(drbd_connection_info_nl_policy), + [DRBD_NLA_CONNECTION_STATISTICS] = NLA_POLICY_NESTED(drbd_connection_statistics_nl_policy), +}; + +/* DRBD_ADM_GET_PEER_DEVICES - dump */ +static const struct nla_policy drbd_get_peer_devices_nl_policy[DRBD_NLA_PEER_DEVICE_STATISTICS + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), + [DRBD_NLA_PEER_DEVICE_INFO] = NLA_POLICY_NESTED(drbd_peer_device_info_nl_policy), + [DRBD_NLA_PEER_DEVICE_STATISTICS] = NLA_POLICY_NESTED(drbd_peer_device_statistics_nl_policy), +}; + +/* DRBD_ADM_GET_INITIAL_STATE - dump */ +static const struct nla_policy drbd_get_initial_state_nl_policy[DRBD_NLA_CFG_CONTEXT + 1] = { + [DRBD_NLA_CFG_CONTEXT] = NLA_POLICY_NESTED(drbd_drbd_cfg_context_nl_policy), +}; + +/* Ops table for drbd */ +const struct genl_split_ops drbd_nl_ops[32] = { + { + .cmd = DRBD_ADM_GET_STATUS, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_get_status_doit, + .post_doit = drbd_post_doit, + .policy = drbd_get_status_do_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_GET_STATUS, + .dumpit = drbd_nl_get_status_dumpit, + .policy = drbd_get_status_dump_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DRBD_ADM_NEW_MINOR, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_new_minor_doit, + .post_doit = drbd_post_doit, + .policy = drbd_new_minor_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_DEL_MINOR, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_del_minor_doit, + .post_doit = drbd_post_doit, + .policy = drbd_del_minor_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_NEW_RESOURCE, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_new_resource_doit, + .post_doit = drbd_post_doit, + .policy = drbd_new_resource_nl_policy, + .maxattr = DRBD_NLA_RESOURCE_OPTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_DEL_RESOURCE, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_del_resource_doit, + .post_doit = drbd_post_doit, + .policy = drbd_del_resource_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_RESOURCE_OPTS, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_resource_opts_doit, + .post_doit = drbd_post_doit, + .policy = drbd_resource_opts_nl_policy, + .maxattr = DRBD_NLA_RESOURCE_OPTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_CONNECT, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_connect_doit, + .post_doit = drbd_post_doit, + .policy = drbd_connect_nl_policy, + .maxattr = DRBD_NLA_NET_CONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_DISCONNECT, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_disconnect_doit, + .post_doit = drbd_post_doit, + .policy = drbd_disconnect_nl_policy, + .maxattr = DRBD_NLA_DISCONNECT_PARMS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_ATTACH, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_attach_doit, + .post_doit = drbd_post_doit, + .policy = drbd_attach_nl_policy, + .maxattr = DRBD_NLA_DISK_CONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_RESIZE, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_resize_doit, + .post_doit = drbd_post_doit, + .policy = drbd_resize_nl_policy, + .maxattr = DRBD_NLA_RESIZE_PARMS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_PRIMARY, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_primary_doit, + .post_doit = drbd_post_doit, + .policy = drbd_primary_nl_policy, + .maxattr = DRBD_NLA_SET_ROLE_PARMS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_SECONDARY, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_secondary_doit, + .post_doit = drbd_post_doit, + .policy = drbd_secondary_nl_policy, + .maxattr = DRBD_NLA_SET_ROLE_PARMS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_NEW_C_UUID, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_new_c_uuid_doit, + .post_doit = drbd_post_doit, + .policy = drbd_new_c_uuid_nl_policy, + .maxattr = DRBD_NLA_NEW_C_UUID_PARMS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_START_OV, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_start_ov_doit, + .post_doit = drbd_post_doit, + .policy = drbd_start_ov_nl_policy, + .maxattr = DRBD_NLA_START_OV_PARMS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_DETACH, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_detach_doit, + .post_doit = drbd_post_doit, + .policy = drbd_detach_nl_policy, + .maxattr = DRBD_NLA_DETACH_PARMS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_INVALIDATE, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_invalidate_doit, + .post_doit = drbd_post_doit, + .policy = drbd_invalidate_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_INVAL_PEER, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_inval_peer_doit, + .post_doit = drbd_post_doit, + .policy = drbd_inval_peer_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_PAUSE_SYNC, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_pause_sync_doit, + .post_doit = drbd_post_doit, + .policy = drbd_pause_sync_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_RESUME_SYNC, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_resume_sync_doit, + .post_doit = drbd_post_doit, + .policy = drbd_resume_sync_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_SUSPEND_IO, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_suspend_io_doit, + .post_doit = drbd_post_doit, + .policy = drbd_suspend_io_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_RESUME_IO, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_resume_io_doit, + .post_doit = drbd_post_doit, + .policy = drbd_resume_io_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_OUTDATE, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_outdate_doit, + .post_doit = drbd_post_doit, + .policy = drbd_outdate_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_GET_TIMEOUT_TYPE, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_get_timeout_type_doit, + .post_doit = drbd_post_doit, + .policy = drbd_get_timeout_type_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_DOWN, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_down_doit, + .post_doit = drbd_post_doit, + .policy = drbd_down_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_CHG_DISK_OPTS, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_chg_disk_opts_doit, + .post_doit = drbd_post_doit, + .policy = drbd_chg_disk_opts_nl_policy, + .maxattr = DRBD_NLA_DISK_CONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_CHG_NET_OPTS, + .pre_doit = drbd_pre_doit, + .doit = drbd_nl_chg_net_opts_doit, + .post_doit = drbd_post_doit, + .policy = drbd_chg_net_opts_nl_policy, + .maxattr = DRBD_NLA_NET_CONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRBD_ADM_GET_RESOURCES, + .dumpit = drbd_nl_get_resources_dumpit, + .policy = drbd_get_resources_nl_policy, + .maxattr = DRBD_NLA_RESOURCE_STATISTICS, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DRBD_ADM_GET_DEVICES, + .dumpit = drbd_nl_get_devices_dumpit, + .done = drbd_adm_dump_devices_done, + .policy = drbd_get_devices_nl_policy, + .maxattr = DRBD_NLA_DEVICE_STATISTICS, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DRBD_ADM_GET_CONNECTIONS, + .dumpit = drbd_nl_get_connections_dumpit, + .done = drbd_adm_dump_connections_done, + .policy = drbd_get_connections_nl_policy, + .maxattr = DRBD_NLA_CONNECTION_STATISTICS, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DRBD_ADM_GET_PEER_DEVICES, + .dumpit = drbd_nl_get_peer_devices_dumpit, + .done = drbd_adm_dump_peer_devices_done, + .policy = drbd_get_peer_devices_nl_policy, + .maxattr = DRBD_NLA_PEER_DEVICE_STATISTICS, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DRBD_ADM_GET_INITIAL_STATE, + .dumpit = drbd_nl_get_initial_state_dumpit, + .policy = drbd_get_initial_state_nl_policy, + .maxattr = DRBD_NLA_CFG_CONTEXT, + .flags = GENL_CMD_CAP_DUMP, + }, +}; + +static const struct genl_multicast_group drbd_nl_mcgrps[] = { + [DRBD_NLGRP_EVENTS] = { "events", }, +}; + +static int __drbd_cfg_context_from_attrs(struct drbd_cfg_context *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR; + struct nlattr *tla = info->attrs[DRBD_NLA_CFG_CONTEXT]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_drbd_cfg_context_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_DRBD_CFG_CONTEXT_CTX_VOLUME]; + if (nla && s) + s->ctx_volume = nla_get_u32(nla); + + nla = ntb[DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME]; + if (nla && s) + s->ctx_resource_name_len = nla_strscpy(s->ctx_resource_name, nla, 128); + + nla = ntb[DRBD_A_DRBD_CFG_CONTEXT_CTX_MY_ADDR]; + if (nla && s) + s->ctx_my_addr_len = nla_memcpy(s->ctx_my_addr, nla, 128); + + nla = ntb[DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR]; + if (nla && s) + s->ctx_peer_addr_len = nla_memcpy(s->ctx_peer_addr, nla, 128); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int drbd_cfg_context_from_attrs(struct drbd_cfg_context *s, + struct genl_info *info) +{ + return __drbd_cfg_context_from_attrs(s, NULL, info); +} + +int drbd_cfg_context_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __drbd_cfg_context_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __disk_conf_from_attrs(struct disk_conf *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_DISK_CONF_DISABLE_WRITE_SAME; + struct nlattr *tla = info->attrs[DRBD_NLA_DISK_CONF]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_DISK_CONF_DISABLE_WRITE_SAME + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_disk_conf_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_DISK_CONF_BACKING_DEV]; + if (nla) { + if (s) + s->backing_dev_len = nla_strscpy(s->backing_dev, nla, 128); + } else { + pr_info("<< missing required attr: backing_dev\n"); + err = -ENOMSG; + } + + nla = ntb[DRBD_A_DISK_CONF_META_DEV]; + if (nla) { + if (s) + s->meta_dev_len = nla_strscpy(s->meta_dev, nla, 128); + } else { + pr_info("<< missing required attr: meta_dev\n"); + err = -ENOMSG; + } + + nla = ntb[DRBD_A_DISK_CONF_META_DEV_IDX]; + if (nla) { + if (s) + s->meta_dev_idx = nla_get_s32(nla); + } else { + pr_info("<< missing required attr: meta_dev_idx\n"); + err = -ENOMSG; + } + + nla = ntb[DRBD_A_DISK_CONF_DISK_SIZE]; + if (nla && s) + s->disk_size = nla_get_u64(nla); + + nla = ntb[DRBD_A_DISK_CONF_MAX_BIO_BVECS]; + if (nla && s) + s->max_bio_bvecs = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_ON_IO_ERROR]; + if (nla && s) + s->on_io_error = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_FENCING]; + if (nla && s) + s->fencing = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_RESYNC_RATE]; + if (nla && s) + s->resync_rate = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_RESYNC_AFTER]; + if (nla && s) + s->resync_after = nla_get_s32(nla); + + nla = ntb[DRBD_A_DISK_CONF_AL_EXTENTS]; + if (nla && s) + s->al_extents = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_C_PLAN_AHEAD]; + if (nla && s) + s->c_plan_ahead = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_C_DELAY_TARGET]; + if (nla && s) + s->c_delay_target = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_C_FILL_TARGET]; + if (nla && s) + s->c_fill_target = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_C_MAX_RATE]; + if (nla && s) + s->c_max_rate = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_C_MIN_RATE]; + if (nla && s) + s->c_min_rate = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_DISK_BARRIER]; + if (nla && s) + s->disk_barrier = nla_get_u8(nla); + + nla = ntb[DRBD_A_DISK_CONF_DISK_FLUSHES]; + if (nla && s) + s->disk_flushes = nla_get_u8(nla); + + nla = ntb[DRBD_A_DISK_CONF_DISK_DRAIN]; + if (nla && s) + s->disk_drain = nla_get_u8(nla); + + nla = ntb[DRBD_A_DISK_CONF_MD_FLUSHES]; + if (nla && s) + s->md_flushes = nla_get_u8(nla); + + nla = ntb[DRBD_A_DISK_CONF_DISK_TIMEOUT]; + if (nla && s) + s->disk_timeout = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_READ_BALANCING]; + if (nla && s) + s->read_balancing = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_AL_UPDATES]; + if (nla && s) + s->al_updates = nla_get_u8(nla); + + nla = ntb[DRBD_A_DISK_CONF_DISCARD_ZEROES_IF_ALIGNED]; + if (nla && s) + s->discard_zeroes_if_aligned = nla_get_u8(nla); + + nla = ntb[DRBD_A_DISK_CONF_RS_DISCARD_GRANULARITY]; + if (nla && s) + s->rs_discard_granularity = nla_get_u32(nla); + + nla = ntb[DRBD_A_DISK_CONF_DISABLE_WRITE_SAME]; + if (nla && s) + s->disable_write_same = nla_get_u8(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int disk_conf_from_attrs(struct disk_conf *s, + struct genl_info *info) +{ + return __disk_conf_from_attrs(s, NULL, info); +} + +int disk_conf_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __disk_conf_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __res_opts_from_attrs(struct res_opts *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_RES_OPTS_ON_NO_DATA; + struct nlattr *tla = info->attrs[DRBD_NLA_RESOURCE_OPTS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_RES_OPTS_ON_NO_DATA + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_res_opts_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_RES_OPTS_CPU_MASK]; + if (nla && s) + s->cpu_mask_len = nla_strscpy(s->cpu_mask, nla, DRBD_CPU_MASK_SIZE); + + nla = ntb[DRBD_A_RES_OPTS_ON_NO_DATA]; + if (nla && s) + s->on_no_data = nla_get_u32(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int res_opts_from_attrs(struct res_opts *s, + struct genl_info *info) +{ + return __res_opts_from_attrs(s, NULL, info); +} + +int res_opts_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __res_opts_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __net_conf_from_attrs(struct net_conf *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_NET_CONF_SOCK_CHECK_TIMEO; + struct nlattr *tla = info->attrs[DRBD_NLA_NET_CONF]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_NET_CONF_SOCK_CHECK_TIMEO + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_net_conf_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_NET_CONF_SHARED_SECRET]; + if (nla && s) + s->shared_secret_len = nla_strscpy(s->shared_secret, nla, SHARED_SECRET_MAX); + + nla = ntb[DRBD_A_NET_CONF_CRAM_HMAC_ALG]; + if (nla && s) + s->cram_hmac_alg_len = nla_strscpy(s->cram_hmac_alg, nla, SHARED_SECRET_MAX); + + nla = ntb[DRBD_A_NET_CONF_INTEGRITY_ALG]; + if (nla && s) + s->integrity_alg_len = nla_strscpy(s->integrity_alg, nla, SHARED_SECRET_MAX); + + nla = ntb[DRBD_A_NET_CONF_VERIFY_ALG]; + if (nla && s) + s->verify_alg_len = nla_strscpy(s->verify_alg, nla, SHARED_SECRET_MAX); + + nla = ntb[DRBD_A_NET_CONF_CSUMS_ALG]; + if (nla && s) + s->csums_alg_len = nla_strscpy(s->csums_alg, nla, SHARED_SECRET_MAX); + + nla = ntb[DRBD_A_NET_CONF_WIRE_PROTOCOL]; + if (nla && s) + s->wire_protocol = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_CONNECT_INT]; + if (nla && s) + s->connect_int = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_TIMEOUT]; + if (nla && s) + s->timeout = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_PING_INT]; + if (nla && s) + s->ping_int = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_PING_TIMEO]; + if (nla && s) + s->ping_timeo = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_SNDBUF_SIZE]; + if (nla && s) + s->sndbuf_size = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_RCVBUF_SIZE]; + if (nla && s) + s->rcvbuf_size = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_KO_COUNT]; + if (nla && s) + s->ko_count = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_MAX_BUFFERS]; + if (nla && s) + s->max_buffers = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_MAX_EPOCH_SIZE]; + if (nla && s) + s->max_epoch_size = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_UNPLUG_WATERMARK]; + if (nla && s) + s->unplug_watermark = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_AFTER_SB_0P]; + if (nla && s) + s->after_sb_0p = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_AFTER_SB_1P]; + if (nla && s) + s->after_sb_1p = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_AFTER_SB_2P]; + if (nla && s) + s->after_sb_2p = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_RR_CONFLICT]; + if (nla && s) + s->rr_conflict = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_ON_CONGESTION]; + if (nla && s) + s->on_congestion = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_CONG_FILL]; + if (nla && s) + s->cong_fill = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_CONG_EXTENTS]; + if (nla && s) + s->cong_extents = nla_get_u32(nla); + + nla = ntb[DRBD_A_NET_CONF_TWO_PRIMARIES]; + if (nla && s) + s->two_primaries = nla_get_u8(nla); + + nla = ntb[DRBD_A_NET_CONF_DISCARD_MY_DATA]; + if (nla && s) + s->discard_my_data = nla_get_u8(nla); + + nla = ntb[DRBD_A_NET_CONF_TCP_CORK]; + if (nla && s) + s->tcp_cork = nla_get_u8(nla); + + nla = ntb[DRBD_A_NET_CONF_ALWAYS_ASBP]; + if (nla && s) + s->always_asbp = nla_get_u8(nla); + + nla = ntb[DRBD_A_NET_CONF_TENTATIVE]; + if (nla && s) + s->tentative = nla_get_u8(nla); + + nla = ntb[DRBD_A_NET_CONF_USE_RLE]; + if (nla && s) + s->use_rle = nla_get_u8(nla); + + nla = ntb[DRBD_A_NET_CONF_CSUMS_AFTER_CRASH_ONLY]; + if (nla && s) + s->csums_after_crash_only = nla_get_u8(nla); + + nla = ntb[DRBD_A_NET_CONF_SOCK_CHECK_TIMEO]; + if (nla && s) + s->sock_check_timeo = nla_get_u32(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int net_conf_from_attrs(struct net_conf *s, + struct genl_info *info) +{ + return __net_conf_from_attrs(s, NULL, info); +} + +int net_conf_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __net_conf_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __set_role_parms_from_attrs(struct set_role_parms *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE; + struct nlattr *tla = info->attrs[DRBD_NLA_SET_ROLE_PARMS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_set_role_parms_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE]; + if (nla && s) + s->assume_uptodate = nla_get_u8(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int set_role_parms_from_attrs(struct set_role_parms *s, + struct genl_info *info) +{ + return __set_role_parms_from_attrs(s, NULL, info); +} + +int set_role_parms_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __set_role_parms_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __resize_parms_from_attrs(struct resize_parms *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE; + struct nlattr *tla = info->attrs[DRBD_NLA_RESIZE_PARMS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_resize_parms_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_RESIZE_PARMS_RESIZE_SIZE]; + if (nla && s) + s->resize_size = nla_get_u64(nla); + + nla = ntb[DRBD_A_RESIZE_PARMS_RESIZE_FORCE]; + if (nla && s) + s->resize_force = nla_get_u8(nla); + + nla = ntb[DRBD_A_RESIZE_PARMS_NO_RESYNC]; + if (nla && s) + s->no_resync = nla_get_u8(nla); + + nla = ntb[DRBD_A_RESIZE_PARMS_AL_STRIPES]; + if (nla && s) + s->al_stripes = nla_get_u32(nla); + + nla = ntb[DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE]; + if (nla && s) + s->al_stripe_size = nla_get_u32(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int resize_parms_from_attrs(struct resize_parms *s, + struct genl_info *info) +{ + return __resize_parms_from_attrs(s, NULL, info); +} + +int resize_parms_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __resize_parms_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __start_ov_parms_from_attrs(struct start_ov_parms *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_START_OV_PARMS_OV_STOP_SECTOR; + struct nlattr *tla = info->attrs[DRBD_NLA_START_OV_PARMS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_START_OV_PARMS_OV_STOP_SECTOR + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_start_ov_parms_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_START_OV_PARMS_OV_START_SECTOR]; + if (nla && s) + s->ov_start_sector = nla_get_u64(nla); + + nla = ntb[DRBD_A_START_OV_PARMS_OV_STOP_SECTOR]; + if (nla && s) + s->ov_stop_sector = nla_get_u64(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int start_ov_parms_from_attrs(struct start_ov_parms *s, + struct genl_info *info) +{ + return __start_ov_parms_from_attrs(s, NULL, info); +} + +int start_ov_parms_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __start_ov_parms_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __new_c_uuid_parms_from_attrs(struct new_c_uuid_parms *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM; + struct nlattr *tla = info->attrs[DRBD_NLA_NEW_C_UUID_PARMS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_new_c_uuid_parms_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM]; + if (nla && s) + s->clear_bm = nla_get_u8(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int new_c_uuid_parms_from_attrs(struct new_c_uuid_parms *s, + struct genl_info *info) +{ + return __new_c_uuid_parms_from_attrs(s, NULL, info); +} + +int new_c_uuid_parms_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __new_c_uuid_parms_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __disconnect_parms_from_attrs(struct disconnect_parms *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT; + struct nlattr *tla = info->attrs[DRBD_NLA_DISCONNECT_PARMS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_disconnect_parms_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT]; + if (nla && s) + s->force_disconnect = nla_get_u8(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int disconnect_parms_from_attrs(struct disconnect_parms *s, + struct genl_info *info) +{ + return __disconnect_parms_from_attrs(s, NULL, info); +} + +int disconnect_parms_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __disconnect_parms_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __detach_parms_from_attrs(struct detach_parms *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_DETACH_PARMS_FORCE_DETACH; + struct nlattr *tla = info->attrs[DRBD_NLA_DETACH_PARMS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_DETACH_PARMS_FORCE_DETACH + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_detach_parms_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_DETACH_PARMS_FORCE_DETACH]; + if (nla && s) + s->force_detach = nla_get_u8(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int detach_parms_from_attrs(struct detach_parms *s, + struct genl_info *info) +{ + return __detach_parms_from_attrs(s, NULL, info); +} + +int detach_parms_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __detach_parms_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __resource_info_from_attrs(struct resource_info *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_RESOURCE_INFO_RES_SUSP_FEN; + struct nlattr *tla = info->attrs[DRBD_NLA_RESOURCE_INFO]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_RESOURCE_INFO_RES_SUSP_FEN + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_resource_info_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_RESOURCE_INFO_RES_ROLE]; + if (nla && s) + s->res_role = nla_get_u32(nla); + + nla = ntb[DRBD_A_RESOURCE_INFO_RES_SUSP]; + if (nla && s) + s->res_susp = nla_get_u8(nla); + + nla = ntb[DRBD_A_RESOURCE_INFO_RES_SUSP_NOD]; + if (nla && s) + s->res_susp_nod = nla_get_u8(nla); + + nla = ntb[DRBD_A_RESOURCE_INFO_RES_SUSP_FEN]; + if (nla && s) + s->res_susp_fen = nla_get_u8(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int resource_info_from_attrs(struct resource_info *s, + struct genl_info *info) +{ + return __resource_info_from_attrs(s, NULL, info); +} + +int resource_info_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __resource_info_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __device_info_from_attrs(struct device_info *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_DEVICE_INFO_DEV_DISK_STATE; + struct nlattr *tla = info->attrs[DRBD_NLA_DEVICE_INFO]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_DEVICE_INFO_DEV_DISK_STATE + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_device_info_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_DEVICE_INFO_DEV_DISK_STATE]; + if (nla && s) + s->dev_disk_state = nla_get_u32(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int device_info_from_attrs(struct device_info *s, + struct genl_info *info) +{ + return __device_info_from_attrs(s, NULL, info); +} + +int device_info_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __device_info_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __connection_info_from_attrs(struct connection_info *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_CONNECTION_INFO_CONN_ROLE; + struct nlattr *tla = info->attrs[DRBD_NLA_CONNECTION_INFO]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_CONNECTION_INFO_CONN_ROLE + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_connection_info_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_CONNECTION_INFO_CONN_CONNECTION_STATE]; + if (nla && s) + s->conn_connection_state = nla_get_u32(nla); + + nla = ntb[DRBD_A_CONNECTION_INFO_CONN_ROLE]; + if (nla && s) + s->conn_role = nla_get_u32(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int connection_info_from_attrs(struct connection_info *s, + struct genl_info *info) +{ + return __connection_info_from_attrs(s, NULL, info); +} + +int connection_info_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __connection_info_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __peer_device_info_from_attrs(struct peer_device_info *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY; + struct nlattr *tla = info->attrs[DRBD_NLA_PEER_DEVICE_INFO]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_peer_device_info_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_PEER_DEVICE_INFO_PEER_REPL_STATE]; + if (nla && s) + s->peer_repl_state = nla_get_u32(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_INFO_PEER_DISK_STATE]; + if (nla && s) + s->peer_disk_state = nla_get_u32(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_USER]; + if (nla && s) + s->peer_resync_susp_user = nla_get_u32(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_PEER]; + if (nla && s) + s->peer_resync_susp_peer = nla_get_u32(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY]; + if (nla && s) + s->peer_resync_susp_dependency = nla_get_u32(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int peer_device_info_from_attrs(struct peer_device_info *s, + struct genl_info *info) +{ + return __peer_device_info_from_attrs(s, NULL, info); +} + +int peer_device_info_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __peer_device_info_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __resource_statistics_from_attrs(struct resource_statistics *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING; + struct nlattr *tla = info->attrs[DRBD_NLA_RESOURCE_STATISTICS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_resource_statistics_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING]; + if (nla && s) + s->res_stat_write_ordering = nla_get_u32(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int resource_statistics_from_attrs(struct resource_statistics *s, + struct genl_info *info) +{ + return __resource_statistics_from_attrs(s, NULL, info); +} + +int resource_statistics_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __resource_statistics_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __device_statistics_from_attrs(struct device_statistics *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS; + struct nlattr *tla = info->attrs[DRBD_NLA_DEVICE_STATISTICS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_device_statistics_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_SIZE]; + if (nla && s) + s->dev_size = nla_get_u64(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_READ]; + if (nla && s) + s->dev_read = nla_get_u64(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_WRITE]; + if (nla && s) + s->dev_write = nla_get_u64(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_AL_WRITES]; + if (nla && s) + s->dev_al_writes = nla_get_u64(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_BM_WRITES]; + if (nla && s) + s->dev_bm_writes = nla_get_u64(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_UPPER_PENDING]; + if (nla && s) + s->dev_upper_pending = nla_get_u32(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_LOWER_PENDING]; + if (nla && s) + s->dev_lower_pending = nla_get_u32(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_UPPER_BLOCKED]; + if (nla && s) + s->dev_upper_blocked = nla_get_u8(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_LOWER_BLOCKED]; + if (nla && s) + s->dev_lower_blocked = nla_get_u8(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_AL_SUSPENDED]; + if (nla && s) + s->dev_al_suspended = nla_get_u8(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_EXPOSED_DATA_UUID]; + if (nla && s) + s->dev_exposed_data_uuid = nla_get_u64(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_CURRENT_UUID]; + if (nla && s) + s->dev_current_uuid = nla_get_u64(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_DEV_DISK_FLAGS]; + if (nla && s) + s->dev_disk_flags = nla_get_u32(nla); + + nla = ntb[DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS]; + if (nla && s) + s->history_uuids_len = nla_memcpy(s->history_uuids, nla, DRBD_NL_HISTORY_UUIDS_SIZE); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int device_statistics_from_attrs(struct device_statistics *s, + struct genl_info *info) +{ + return __device_statistics_from_attrs(s, NULL, info); +} + +int device_statistics_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __device_statistics_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __connection_statistics_from_attrs(struct connection_statistics *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED; + struct nlattr *tla = info->attrs[DRBD_NLA_CONNECTION_STATISTICS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_connection_statistics_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED]; + if (nla && s) + s->conn_congested = nla_get_u8(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int connection_statistics_from_attrs(struct connection_statistics *s, + struct genl_info *info) +{ + return __connection_statistics_from_attrs(s, NULL, info); +} + +int connection_statistics_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __connection_statistics_from_attrs(NULL, ret_nested_attribute_table, info); +} + +static int __peer_device_statistics_from_attrs(struct peer_device_statistics *s, + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + const int maxtype = DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS; + struct nlattr *tla = info->attrs[DRBD_NLA_PEER_DEVICE_STATISTICS]; + struct nlattr **ntb; + struct nlattr *nla; + int err = 0; + + if (ret_nested_attribute_table) + *ret_nested_attribute_table = NULL; + if (!tla) + return -ENOMSG; + ntb = kcalloc(DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS + 1, sizeof(*ntb), GFP_KERNEL); + if (!ntb) + return -ENOMEM; + err = nla_parse_nested_deprecated(ntb, maxtype, tla, drbd_peer_device_statistics_nl_policy, NULL); + if (err) + goto out; + + nla = ntb[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_RECEIVED]; + if (nla && s) + s->peer_dev_received = nla_get_u64(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_SENT]; + if (nla && s) + s->peer_dev_sent = nla_get_u64(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_PENDING]; + if (nla && s) + s->peer_dev_pending = nla_get_u32(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_UNACKED]; + if (nla && s) + s->peer_dev_unacked = nla_get_u32(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_OUT_OF_SYNC]; + if (nla && s) + s->peer_dev_out_of_sync = nla_get_u64(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_RESYNC_FAILED]; + if (nla && s) + s->peer_dev_resync_failed = nla_get_u64(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_BITMAP_UUID]; + if (nla && s) + s->peer_dev_bitmap_uuid = nla_get_u64(nla); + + nla = ntb[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS]; + if (nla && s) + s->peer_dev_flags = nla_get_u32(nla); + +out: + if (ret_nested_attribute_table && (!err || err == -ENOMSG)) + *ret_nested_attribute_table = ntb; + else + kfree(ntb); + return err; +} + +int peer_device_statistics_from_attrs(struct peer_device_statistics *s, + struct genl_info *info) +{ + return __peer_device_statistics_from_attrs(s, NULL, info); +} + +int peer_device_statistics_ntb_from_attrs( + struct nlattr ***ret_nested_attribute_table, + struct genl_info *info) +{ + return __peer_device_statistics_from_attrs(NULL, ret_nested_attribute_table, info); +} + +int drbd_cfg_reply_to_skb(struct sk_buff *skb, struct drbd_cfg_reply *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY); + + if (!tla) + goto nla_put_failure; + + if (nla_put(skb, DRBD_A_DRBD_CFG_REPLY_INFO_TEXT, min_t(int, 0, + s->info_text_len + (s->info_text_len < 0)), s->info_text)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int drbd_cfg_context_to_skb(struct sk_buff *skb, struct drbd_cfg_context *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_DRBD_CFG_CONTEXT_CTX_VOLUME, s->ctx_volume)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME, min_t(int, 128, + s->ctx_resource_name_len + (s->ctx_resource_name_len < 128)), s->ctx_resource_name)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_DRBD_CFG_CONTEXT_CTX_MY_ADDR, min_t(int, 128, + s->ctx_my_addr_len), s->ctx_my_addr)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR, min_t(int, 128, + s->ctx_peer_addr_len), s->ctx_peer_addr)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int disk_conf_to_skb(struct sk_buff *skb, struct disk_conf *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_DISK_CONF); + + if (!tla) + goto nla_put_failure; + + if (nla_put(skb, DRBD_A_DISK_CONF_BACKING_DEV, min_t(int, 128, + s->backing_dev_len + (s->backing_dev_len < 128)), s->backing_dev)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_DISK_CONF_META_DEV, min_t(int, 128, + s->meta_dev_len + (s->meta_dev_len < 128)), s->meta_dev)) + goto nla_put_failure; + if (nla_put_s32(skb, DRBD_A_DISK_CONF_META_DEV_IDX, s->meta_dev_idx)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_DISK_CONF_DISK_SIZE, s->disk_size, 0)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_MAX_BIO_BVECS, s->max_bio_bvecs)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_ON_IO_ERROR, s->on_io_error)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_FENCING, s->fencing)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_RESYNC_RATE, s->resync_rate)) + goto nla_put_failure; + if (nla_put_s32(skb, DRBD_A_DISK_CONF_RESYNC_AFTER, s->resync_after)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_AL_EXTENTS, s->al_extents)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_C_PLAN_AHEAD, s->c_plan_ahead)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_C_DELAY_TARGET, s->c_delay_target)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_C_FILL_TARGET, s->c_fill_target)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_C_MAX_RATE, s->c_max_rate)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_C_MIN_RATE, s->c_min_rate)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DISK_CONF_DISK_BARRIER, s->disk_barrier)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DISK_CONF_DISK_FLUSHES, s->disk_flushes)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DISK_CONF_DISK_DRAIN, s->disk_drain)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DISK_CONF_MD_FLUSHES, s->md_flushes)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_DISK_TIMEOUT, s->disk_timeout)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_READ_BALANCING, s->read_balancing)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DISK_CONF_AL_UPDATES, s->al_updates)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DISK_CONF_DISCARD_ZEROES_IF_ALIGNED, s->discard_zeroes_if_aligned)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DISK_CONF_RS_DISCARD_GRANULARITY, s->rs_discard_granularity)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DISK_CONF_DISABLE_WRITE_SAME, s->disable_write_same)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int res_opts_to_skb(struct sk_buff *skb, struct res_opts *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_RESOURCE_OPTS); + + if (!tla) + goto nla_put_failure; + + if (nla_put(skb, DRBD_A_RES_OPTS_CPU_MASK, min_t(int, DRBD_CPU_MASK_SIZE, + s->cpu_mask_len + (s->cpu_mask_len < DRBD_CPU_MASK_SIZE)), s->cpu_mask)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_RES_OPTS_ON_NO_DATA, s->on_no_data)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int net_conf_to_skb(struct sk_buff *skb, struct net_conf *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_NET_CONF); + + if (!tla) + goto nla_put_failure; + + if (nla_put(skb, DRBD_A_NET_CONF_SHARED_SECRET, min_t(int, SHARED_SECRET_MAX, + s->shared_secret_len + (s->shared_secret_len < SHARED_SECRET_MAX)), s->shared_secret)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_NET_CONF_CRAM_HMAC_ALG, min_t(int, SHARED_SECRET_MAX, + s->cram_hmac_alg_len + (s->cram_hmac_alg_len < SHARED_SECRET_MAX)), s->cram_hmac_alg)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_NET_CONF_INTEGRITY_ALG, min_t(int, SHARED_SECRET_MAX, + s->integrity_alg_len + (s->integrity_alg_len < SHARED_SECRET_MAX)), s->integrity_alg)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_NET_CONF_VERIFY_ALG, min_t(int, SHARED_SECRET_MAX, + s->verify_alg_len + (s->verify_alg_len < SHARED_SECRET_MAX)), s->verify_alg)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_NET_CONF_CSUMS_ALG, min_t(int, SHARED_SECRET_MAX, + s->csums_alg_len + (s->csums_alg_len < SHARED_SECRET_MAX)), s->csums_alg)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_WIRE_PROTOCOL, s->wire_protocol)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_CONNECT_INT, s->connect_int)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_TIMEOUT, s->timeout)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_PING_INT, s->ping_int)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_PING_TIMEO, s->ping_timeo)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_SNDBUF_SIZE, s->sndbuf_size)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_RCVBUF_SIZE, s->rcvbuf_size)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_KO_COUNT, s->ko_count)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_MAX_BUFFERS, s->max_buffers)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_MAX_EPOCH_SIZE, s->max_epoch_size)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_UNPLUG_WATERMARK, s->unplug_watermark)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_AFTER_SB_0P, s->after_sb_0p)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_AFTER_SB_1P, s->after_sb_1p)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_AFTER_SB_2P, s->after_sb_2p)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_RR_CONFLICT, s->rr_conflict)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_ON_CONGESTION, s->on_congestion)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_CONG_FILL, s->cong_fill)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_CONG_EXTENTS, s->cong_extents)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_NET_CONF_TWO_PRIMARIES, s->two_primaries)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_NET_CONF_DISCARD_MY_DATA, s->discard_my_data)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_NET_CONF_TCP_CORK, s->tcp_cork)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_NET_CONF_ALWAYS_ASBP, s->always_asbp)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_NET_CONF_TENTATIVE, s->tentative)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_NET_CONF_USE_RLE, s->use_rle)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_NET_CONF_CSUMS_AFTER_CRASH_ONLY, s->csums_after_crash_only)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_NET_CONF_SOCK_CHECK_TIMEO, s->sock_check_timeo)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int set_role_parms_to_skb(struct sk_buff *skb, struct set_role_parms *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_SET_ROLE_PARMS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u8(skb, DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE, s->assume_uptodate)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int resize_parms_to_skb(struct sk_buff *skb, struct resize_parms *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_RESIZE_PARMS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, DRBD_A_RESIZE_PARMS_RESIZE_SIZE, s->resize_size, 0)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_RESIZE_PARMS_RESIZE_FORCE, s->resize_force)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_RESIZE_PARMS_NO_RESYNC, s->no_resync)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_RESIZE_PARMS_AL_STRIPES, s->al_stripes)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE, s->al_stripe_size)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int state_info_to_skb(struct sk_buff *skb, struct state_info *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_STATE_INFO); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_STATE_INFO_SIB_REASON, s->sib_reason)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_STATE_INFO_CURRENT_STATE, s->current_state)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_CAPACITY, s->capacity, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_ED_UUID, s->ed_uuid, 0)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_STATE_INFO_PREV_STATE, s->prev_state)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_STATE_INFO_NEW_STATE, s->new_state)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_STATE_INFO_UUIDS, min_t(int, DRBD_NL_UUIDS_SIZE, + s->uuids_len), s->uuids)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_STATE_INFO_DISK_FLAGS, s->disk_flags)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BITS_TOTAL, s->bits_total, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BITS_OOS, s->bits_oos, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BITS_RS_TOTAL, s->bits_rs_total, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BITS_RS_FAILED, s->bits_rs_failed, 0)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_STATE_INFO_HELPER, min_t(int, 32, + s->helper_len + (s->helper_len < 32)), s->helper)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_STATE_INFO_HELPER_EXIT_CODE, s->helper_exit_code)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_SEND_CNT, s->send_cnt, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_RECV_CNT, s->recv_cnt, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_READ_CNT, s->read_cnt, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_WRIT_CNT, s->writ_cnt, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_AL_WRIT_CNT, s->al_writ_cnt, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_STATE_INFO_BM_WRIT_CNT, s->bm_writ_cnt, 0)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_STATE_INFO_AP_BIO_CNT, s->ap_bio_cnt)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_STATE_INFO_AP_PENDING_CNT, s->ap_pending_cnt)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_STATE_INFO_RS_PENDING_CNT, s->rs_pending_cnt)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int start_ov_parms_to_skb(struct sk_buff *skb, struct start_ov_parms *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_START_OV_PARMS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, DRBD_A_START_OV_PARMS_OV_START_SECTOR, s->ov_start_sector, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_START_OV_PARMS_OV_STOP_SECTOR, s->ov_stop_sector, 0)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int new_c_uuid_parms_to_skb(struct sk_buff *skb, struct new_c_uuid_parms *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_NEW_C_UUID_PARMS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u8(skb, DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM, s->clear_bm)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int timeout_parms_to_skb(struct sk_buff *skb, struct timeout_parms *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_TIMEOUT_PARMS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_TIMEOUT_PARMS_TIMEOUT_TYPE, s->timeout_type)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int disconnect_parms_to_skb(struct sk_buff *skb, struct disconnect_parms *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_DISCONNECT_PARMS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u8(skb, DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT, s->force_disconnect)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int detach_parms_to_skb(struct sk_buff *skb, struct detach_parms *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_DETACH_PARMS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u8(skb, DRBD_A_DETACH_PARMS_FORCE_DETACH, s->force_detach)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int resource_info_to_skb(struct sk_buff *skb, struct resource_info *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_RESOURCE_INFO); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_RESOURCE_INFO_RES_ROLE, s->res_role)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_RESOURCE_INFO_RES_SUSP, s->res_susp)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_RESOURCE_INFO_RES_SUSP_NOD, s->res_susp_nod)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_RESOURCE_INFO_RES_SUSP_FEN, s->res_susp_fen)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int device_info_to_skb(struct sk_buff *skb, struct device_info *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_DEVICE_INFO); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_DEVICE_INFO_DEV_DISK_STATE, s->dev_disk_state)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int connection_info_to_skb(struct sk_buff *skb, struct connection_info *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_CONNECTION_INFO); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_CONNECTION_INFO_CONN_CONNECTION_STATE, s->conn_connection_state)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_CONNECTION_INFO_CONN_ROLE, s->conn_role)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int peer_device_info_to_skb(struct sk_buff *skb, struct peer_device_info *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_PEER_DEVICE_INFO); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_PEER_DEVICE_INFO_PEER_REPL_STATE, s->peer_repl_state)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_PEER_DEVICE_INFO_PEER_DISK_STATE, s->peer_disk_state)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_USER, s->peer_resync_susp_user)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_PEER, s->peer_resync_susp_peer)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY, s->peer_resync_susp_dependency)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int resource_statistics_to_skb(struct sk_buff *skb, struct resource_statistics *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_RESOURCE_STATISTICS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING, s->res_stat_write_ordering)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int device_statistics_to_skb(struct sk_buff *skb, struct device_statistics *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_DEVICE_STATISTICS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, DRBD_A_DEVICE_STATISTICS_DEV_SIZE, s->dev_size, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_DEVICE_STATISTICS_DEV_READ, s->dev_read, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_DEVICE_STATISTICS_DEV_WRITE, s->dev_write, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_DEVICE_STATISTICS_DEV_AL_WRITES, s->dev_al_writes, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_DEVICE_STATISTICS_DEV_BM_WRITES, s->dev_bm_writes, 0)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DEVICE_STATISTICS_DEV_UPPER_PENDING, s->dev_upper_pending)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DEVICE_STATISTICS_DEV_LOWER_PENDING, s->dev_lower_pending)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DEVICE_STATISTICS_DEV_UPPER_BLOCKED, s->dev_upper_blocked)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DEVICE_STATISTICS_DEV_LOWER_BLOCKED, s->dev_lower_blocked)) + goto nla_put_failure; + if (nla_put_u8(skb, DRBD_A_DEVICE_STATISTICS_DEV_AL_SUSPENDED, s->dev_al_suspended)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_DEVICE_STATISTICS_DEV_EXPOSED_DATA_UUID, s->dev_exposed_data_uuid, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_DEVICE_STATISTICS_DEV_CURRENT_UUID, s->dev_current_uuid, 0)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DEVICE_STATISTICS_DEV_DISK_FLAGS, s->dev_disk_flags)) + goto nla_put_failure; + if (nla_put(skb, DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS, min_t(int, DRBD_NL_HISTORY_UUIDS_SIZE, + s->history_uuids_len), s->history_uuids)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int connection_statistics_to_skb(struct sk_buff *skb, struct connection_statistics *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_CONNECTION_STATISTICS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u8(skb, DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED, s->conn_congested)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int peer_device_statistics_to_skb(struct sk_buff *skb, struct peer_device_statistics *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_PEER_DEVICE_STATISTICS); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_RECEIVED, s->peer_dev_received, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_SENT, s->peer_dev_sent, 0)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_PENDING, s->peer_dev_pending)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_UNACKED, s->peer_dev_unacked)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_OUT_OF_SYNC, s->peer_dev_out_of_sync, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_RESYNC_FAILED, s->peer_dev_resync_failed, 0)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_BITMAP_UUID, s->peer_dev_bitmap_uuid, 0)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS, s->peer_dev_flags)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int drbd_notification_header_to_skb(struct sk_buff *skb, struct drbd_notification_header *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_NOTIFICATION_HEADER); + + if (!tla) + goto nla_put_failure; + + if (nla_put_u32(skb, DRBD_A_DRBD_NOTIFICATION_HEADER_NH_TYPE, s->nh_type)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +int drbd_helper_info_to_skb(struct sk_buff *skb, struct drbd_helper_info *s) +{ + struct nlattr *tla = nla_nest_start(skb, DRBD_NLA_HELPER); + + if (!tla) + goto nla_put_failure; + + if (nla_put(skb, DRBD_A_DRBD_HELPER_INFO_HELPER_NAME, min_t(int, 32, + s->helper_name_len + (s->helper_name_len < 32)), s->helper_name)) + goto nla_put_failure; + if (nla_put_u32(skb, DRBD_A_DRBD_HELPER_INFO_HELPER_STATUS, s->helper_status)) + goto nla_put_failure; + + nla_nest_end(skb, tla); + return 0; + +nla_put_failure: + if (tla) + nla_nest_cancel(skb, tla); + return -EMSGSIZE; +} + +void set_disk_conf_defaults(struct disk_conf *x) +{ + x->on_io_error = DRBD_ON_IO_ERROR_DEF; + x->fencing = DRBD_FENCING_DEF; + x->resync_rate = DRBD_RESYNC_RATE_DEF; + x->resync_after = DRBD_MINOR_NUMBER_DEF; + x->al_extents = DRBD_AL_EXTENTS_DEF; + x->c_plan_ahead = DRBD_C_PLAN_AHEAD_DEF; + x->c_delay_target = DRBD_C_DELAY_TARGET_DEF; + x->c_fill_target = DRBD_C_FILL_TARGET_DEF; + x->c_max_rate = DRBD_C_MAX_RATE_DEF; + x->c_min_rate = DRBD_C_MIN_RATE_DEF; + x->disk_barrier = DRBD_DISK_BARRIER_DEF; + x->disk_flushes = DRBD_DISK_FLUSHES_DEF; + x->disk_drain = DRBD_DISK_DRAIN_DEF; + x->md_flushes = DRBD_MD_FLUSHES_DEF; + x->disk_timeout = DRBD_DISK_TIMEOUT_DEF; + x->read_balancing = DRBD_READ_BALANCING_DEF; + x->al_updates = DRBD_AL_UPDATES_DEF; + x->discard_zeroes_if_aligned = DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF; + x->rs_discard_granularity = DRBD_RS_DISCARD_GRANULARITY_DEF; + x->disable_write_same = DRBD_DISABLE_WRITE_SAME_DEF; +} + +void set_res_opts_defaults(struct res_opts *x) +{ + memset(x->cpu_mask, 0, sizeof(x->cpu_mask)); + x->cpu_mask_len = 0; + x->on_no_data = DRBD_ON_NO_DATA_DEF; +} + +void set_net_conf_defaults(struct net_conf *x) +{ + memset(x->shared_secret, 0, sizeof(x->shared_secret)); + x->shared_secret_len = 0; + memset(x->cram_hmac_alg, 0, sizeof(x->cram_hmac_alg)); + x->cram_hmac_alg_len = 0; + memset(x->integrity_alg, 0, sizeof(x->integrity_alg)); + x->integrity_alg_len = 0; + memset(x->verify_alg, 0, sizeof(x->verify_alg)); + x->verify_alg_len = 0; + memset(x->csums_alg, 0, sizeof(x->csums_alg)); + x->csums_alg_len = 0; + x->wire_protocol = DRBD_PROTOCOL_DEF; + x->connect_int = DRBD_CONNECT_INT_DEF; + x->timeout = DRBD_TIMEOUT_DEF; + x->ping_int = DRBD_PING_INT_DEF; + x->ping_timeo = DRBD_PING_TIMEO_DEF; + x->sndbuf_size = DRBD_SNDBUF_SIZE_DEF; + x->rcvbuf_size = DRBD_RCVBUF_SIZE_DEF; + x->ko_count = DRBD_KO_COUNT_DEF; + x->max_buffers = DRBD_MAX_BUFFERS_DEF; + x->max_epoch_size = DRBD_MAX_EPOCH_SIZE_DEF; + x->unplug_watermark = DRBD_UNPLUG_WATERMARK_DEF; + x->after_sb_0p = DRBD_AFTER_SB_0P_DEF; + x->after_sb_1p = DRBD_AFTER_SB_1P_DEF; + x->after_sb_2p = DRBD_AFTER_SB_2P_DEF; + x->rr_conflict = DRBD_RR_CONFLICT_DEF; + x->on_congestion = DRBD_ON_CONGESTION_DEF; + x->cong_fill = DRBD_CONG_FILL_DEF; + x->cong_extents = DRBD_CONG_EXTENTS_DEF; + x->two_primaries = DRBD_ALLOW_TWO_PRIMARIES_DEF; + x->tcp_cork = DRBD_TCP_CORK_DEF; + x->always_asbp = DRBD_ALWAYS_ASBP_DEF; + x->use_rle = DRBD_USE_RLE_DEF; + x->csums_after_crash_only = DRBD_CSUMS_AFTER_CRASH_ONLY_DEF; + x->sock_check_timeo = DRBD_SOCKET_CHECK_TIMEO_DEF; +} + +void set_resize_parms_defaults(struct resize_parms *x) +{ + x->al_stripes = DRBD_AL_STRIPES_DEF; + x->al_stripe_size = DRBD_AL_STRIPE_SIZE_DEF; +} diff --git a/drivers/block/drbd/drbd_nl_gen.h b/drivers/block/drbd/drbd_nl_gen.h new file mode 100644 index 000000000000..f2140dd1ac4e --- /dev/null +++ b/drivers/block/drbd/drbd_nl_gen.h @@ -0,0 +1,395 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ + +#ifndef _LINUX_DRBD_GEN_H +#define _LINUX_DRBD_GEN_H + +#include +#include + +#include +#include +#include + +/* Common nested types */ +extern const struct nla_policy drbd_connection_info_nl_policy[DRBD_A_CONNECTION_INFO_CONN_ROLE + 1]; +extern const struct nla_policy drbd_connection_statistics_nl_policy[DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED + 1]; +extern const struct nla_policy drbd_detach_parms_nl_policy[DRBD_A_DETACH_PARMS_FORCE_DETACH + 1]; +extern const struct nla_policy drbd_device_info_nl_policy[DRBD_A_DEVICE_INFO_DEV_DISK_STATE + 1]; +extern const struct nla_policy drbd_device_statistics_nl_policy[DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS + 1]; +extern const struct nla_policy drbd_disconnect_parms_nl_policy[DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT + 1]; +extern const struct nla_policy drbd_disk_conf_nl_policy[DRBD_A_DISK_CONF_DISABLE_WRITE_SAME + 1]; +extern const struct nla_policy drbd_drbd_cfg_context_nl_policy[DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR + 1]; +extern const struct nla_policy drbd_net_conf_nl_policy[DRBD_A_NET_CONF_SOCK_CHECK_TIMEO + 1]; +extern const struct nla_policy drbd_new_c_uuid_parms_nl_policy[DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM + 1]; +extern const struct nla_policy drbd_peer_device_info_nl_policy[DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY + 1]; +extern const struct nla_policy drbd_peer_device_statistics_nl_policy[DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS + 1]; +extern const struct nla_policy drbd_res_opts_nl_policy[DRBD_A_RES_OPTS_ON_NO_DATA + 1]; +extern const struct nla_policy drbd_resize_parms_nl_policy[DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE + 1]; +extern const struct nla_policy drbd_resource_info_nl_policy[DRBD_A_RESOURCE_INFO_RES_SUSP_FEN + 1]; +extern const struct nla_policy drbd_resource_statistics_nl_policy[DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING + 1]; +extern const struct nla_policy drbd_set_role_parms_nl_policy[DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE + 1]; +extern const struct nla_policy drbd_start_ov_parms_nl_policy[DRBD_A_START_OV_PARMS_OV_STOP_SECTOR + 1]; + +/* Ops table for drbd */ +extern const struct genl_split_ops drbd_nl_ops[32]; + +int drbd_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +void +drbd_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +int drbd_adm_dump_devices_done(struct netlink_callback *cb); +int drbd_adm_dump_connections_done(struct netlink_callback *cb); +int drbd_adm_dump_peer_devices_done(struct netlink_callback *cb); + +int drbd_nl_get_status_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_get_status_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int drbd_nl_new_minor_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_del_minor_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_new_resource_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_del_resource_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_resource_opts_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_connect_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_disconnect_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_attach_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_resize_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_primary_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_secondary_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_new_c_uuid_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_start_ov_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_detach_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_invalidate_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_inval_peer_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_pause_sync_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_resume_sync_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_suspend_io_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_resume_io_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_outdate_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_get_timeout_type_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_down_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_chg_disk_opts_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_chg_net_opts_doit(struct sk_buff *skb, struct genl_info *info); +int drbd_nl_get_resources_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int drbd_nl_get_devices_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int drbd_nl_get_connections_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int drbd_nl_get_peer_devices_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int drbd_nl_get_initial_state_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); + +enum { + DRBD_NLGRP_EVENTS, +}; + +struct drbd_cfg_reply { + char info_text[0]; + __u32 info_text_len; +}; + +struct drbd_cfg_context { + __u32 ctx_volume; + char ctx_resource_name[128]; + __u32 ctx_resource_name_len; + char ctx_my_addr[128]; + __u32 ctx_my_addr_len; + char ctx_peer_addr[128]; + __u32 ctx_peer_addr_len; +}; + +struct disk_conf { + char backing_dev[128]; + __u32 backing_dev_len; + char meta_dev[128]; + __u32 meta_dev_len; + __s32 meta_dev_idx; + __u64 disk_size; + __u32 max_bio_bvecs; + __u32 on_io_error; + __u32 fencing; + __u32 resync_rate; + __s32 resync_after; + __u32 al_extents; + __u32 c_plan_ahead; + __u32 c_delay_target; + __u32 c_fill_target; + __u32 c_max_rate; + __u32 c_min_rate; + unsigned char disk_barrier; + unsigned char disk_flushes; + unsigned char disk_drain; + unsigned char md_flushes; + __u32 disk_timeout; + __u32 read_balancing; + unsigned char al_updates; + unsigned char discard_zeroes_if_aligned; + __u32 rs_discard_granularity; + unsigned char disable_write_same; +}; + +struct res_opts { + char cpu_mask[DRBD_CPU_MASK_SIZE]; + __u32 cpu_mask_len; + __u32 on_no_data; +}; + +struct net_conf { + char shared_secret[SHARED_SECRET_MAX]; + __u32 shared_secret_len; + char cram_hmac_alg[SHARED_SECRET_MAX]; + __u32 cram_hmac_alg_len; + char integrity_alg[SHARED_SECRET_MAX]; + __u32 integrity_alg_len; + char verify_alg[SHARED_SECRET_MAX]; + __u32 verify_alg_len; + char csums_alg[SHARED_SECRET_MAX]; + __u32 csums_alg_len; + __u32 wire_protocol; + __u32 connect_int; + __u32 timeout; + __u32 ping_int; + __u32 ping_timeo; + __u32 sndbuf_size; + __u32 rcvbuf_size; + __u32 ko_count; + __u32 max_buffers; + __u32 max_epoch_size; + __u32 unplug_watermark; + __u32 after_sb_0p; + __u32 after_sb_1p; + __u32 after_sb_2p; + __u32 rr_conflict; + __u32 on_congestion; + __u32 cong_fill; + __u32 cong_extents; + unsigned char two_primaries; + unsigned char discard_my_data; + unsigned char tcp_cork; + unsigned char always_asbp; + unsigned char tentative; + unsigned char use_rle; + unsigned char csums_after_crash_only; + __u32 sock_check_timeo; +}; + +struct set_role_parms { + unsigned char assume_uptodate; +}; + +struct resize_parms { + __u64 resize_size; + unsigned char resize_force; + unsigned char no_resync; + __u32 al_stripes; + __u32 al_stripe_size; +}; + +struct state_info { + __u32 sib_reason; + __u32 current_state; + __u64 capacity; + __u64 ed_uuid; + __u32 prev_state; + __u32 new_state; + char uuids[DRBD_NL_UUIDS_SIZE]; + __u32 uuids_len; + __u32 disk_flags; + __u64 bits_total; + __u64 bits_oos; + __u64 bits_rs_total; + __u64 bits_rs_failed; + char helper[32]; + __u32 helper_len; + __u32 helper_exit_code; + __u64 send_cnt; + __u64 recv_cnt; + __u64 read_cnt; + __u64 writ_cnt; + __u64 al_writ_cnt; + __u64 bm_writ_cnt; + __u32 ap_bio_cnt; + __u32 ap_pending_cnt; + __u32 rs_pending_cnt; +}; + +struct start_ov_parms { + __u64 ov_start_sector; + __u64 ov_stop_sector; +}; + +struct new_c_uuid_parms { + unsigned char clear_bm; +}; + +struct timeout_parms { + __u32 timeout_type; +}; + +struct disconnect_parms { + unsigned char force_disconnect; +}; + +struct detach_parms { + unsigned char force_detach; +}; + +struct resource_info { + __u32 res_role; + unsigned char res_susp; + unsigned char res_susp_nod; + unsigned char res_susp_fen; +}; + +struct device_info { + __u32 dev_disk_state; +}; + +struct connection_info { + __u32 conn_connection_state; + __u32 conn_role; +}; + +struct peer_device_info { + __u32 peer_repl_state; + __u32 peer_disk_state; + __u32 peer_resync_susp_user; + __u32 peer_resync_susp_peer; + __u32 peer_resync_susp_dependency; +}; + +struct resource_statistics { + __u32 res_stat_write_ordering; +}; + +struct device_statistics { + __u64 dev_size; + __u64 dev_read; + __u64 dev_write; + __u64 dev_al_writes; + __u64 dev_bm_writes; + __u32 dev_upper_pending; + __u32 dev_lower_pending; + unsigned char dev_upper_blocked; + unsigned char dev_lower_blocked; + unsigned char dev_al_suspended; + __u64 dev_exposed_data_uuid; + __u64 dev_current_uuid; + __u32 dev_disk_flags; + char history_uuids[DRBD_NL_HISTORY_UUIDS_SIZE]; + __u32 history_uuids_len; +}; + +struct connection_statistics { + unsigned char conn_congested; +}; + +struct peer_device_statistics { + __u64 peer_dev_received; + __u64 peer_dev_sent; + __u32 peer_dev_pending; + __u32 peer_dev_unacked; + __u64 peer_dev_out_of_sync; + __u64 peer_dev_resync_failed; + __u64 peer_dev_bitmap_uuid; + __u32 peer_dev_flags; +}; + +struct drbd_notification_header { + __u32 nh_type; +}; + +struct drbd_helper_info { + char helper_name[32]; + __u32 helper_name_len; + __u32 helper_status; +}; + +int drbd_cfg_reply_to_skb(struct sk_buff *skb, struct drbd_cfg_reply *s); + +int drbd_cfg_context_from_attrs(struct drbd_cfg_context *s, struct genl_info *info); +int drbd_cfg_context_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int drbd_cfg_context_to_skb(struct sk_buff *skb, struct drbd_cfg_context *s); + +int disk_conf_from_attrs(struct disk_conf *s, struct genl_info *info); +int disk_conf_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int disk_conf_to_skb(struct sk_buff *skb, struct disk_conf *s); +void set_disk_conf_defaults(struct disk_conf *x); + +int res_opts_from_attrs(struct res_opts *s, struct genl_info *info); +int res_opts_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int res_opts_to_skb(struct sk_buff *skb, struct res_opts *s); +void set_res_opts_defaults(struct res_opts *x); + +int net_conf_from_attrs(struct net_conf *s, struct genl_info *info); +int net_conf_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int net_conf_to_skb(struct sk_buff *skb, struct net_conf *s); +void set_net_conf_defaults(struct net_conf *x); + +int set_role_parms_from_attrs(struct set_role_parms *s, struct genl_info *info); +int set_role_parms_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int set_role_parms_to_skb(struct sk_buff *skb, struct set_role_parms *s); + +int resize_parms_from_attrs(struct resize_parms *s, struct genl_info *info); +int resize_parms_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int resize_parms_to_skb(struct sk_buff *skb, struct resize_parms *s); +void set_resize_parms_defaults(struct resize_parms *x); + +int state_info_to_skb(struct sk_buff *skb, struct state_info *s); + +int start_ov_parms_from_attrs(struct start_ov_parms *s, struct genl_info *info); +int start_ov_parms_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int start_ov_parms_to_skb(struct sk_buff *skb, struct start_ov_parms *s); + +int new_c_uuid_parms_from_attrs(struct new_c_uuid_parms *s, struct genl_info *info); +int new_c_uuid_parms_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int new_c_uuid_parms_to_skb(struct sk_buff *skb, struct new_c_uuid_parms *s); + +int timeout_parms_to_skb(struct sk_buff *skb, struct timeout_parms *s); + +int disconnect_parms_from_attrs(struct disconnect_parms *s, struct genl_info *info); +int disconnect_parms_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int disconnect_parms_to_skb(struct sk_buff *skb, struct disconnect_parms *s); + +int detach_parms_from_attrs(struct detach_parms *s, struct genl_info *info); +int detach_parms_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int detach_parms_to_skb(struct sk_buff *skb, struct detach_parms *s); + +int resource_info_from_attrs(struct resource_info *s, struct genl_info *info); +int resource_info_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int resource_info_to_skb(struct sk_buff *skb, struct resource_info *s); + +int device_info_from_attrs(struct device_info *s, struct genl_info *info); +int device_info_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int device_info_to_skb(struct sk_buff *skb, struct device_info *s); + +int connection_info_from_attrs(struct connection_info *s, struct genl_info *info); +int connection_info_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int connection_info_to_skb(struct sk_buff *skb, struct connection_info *s); + +int peer_device_info_from_attrs(struct peer_device_info *s, struct genl_info *info); +int peer_device_info_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int peer_device_info_to_skb(struct sk_buff *skb, struct peer_device_info *s); + +int resource_statistics_from_attrs(struct resource_statistics *s, struct genl_info *info); +int resource_statistics_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int resource_statistics_to_skb(struct sk_buff *skb, struct resource_statistics *s); + +int device_statistics_from_attrs(struct device_statistics *s, struct genl_info *info); +int device_statistics_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int device_statistics_to_skb(struct sk_buff *skb, struct device_statistics *s); + +int connection_statistics_from_attrs(struct connection_statistics *s, struct genl_info *info); +int connection_statistics_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int connection_statistics_to_skb(struct sk_buff *skb, struct connection_statistics *s); + +int peer_device_statistics_from_attrs(struct peer_device_statistics *s, struct genl_info *info); +int peer_device_statistics_ntb_from_attrs(struct nlattr ***ret_nested_attribute_table, struct genl_info *info); +int peer_device_statistics_to_skb(struct sk_buff *skb, struct peer_device_statistics *s); + +int drbd_notification_header_to_skb(struct sk_buff *skb, struct drbd_notification_header *s); + +int drbd_helper_info_to_skb(struct sk_buff *skb, struct drbd_helper_info *s); + +#endif /* _LINUX_DRBD_GEN_H */ diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index 1d0feafceadc..6d0c12c10260 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -228,7 +228,7 @@ int drbd_seq_show(struct seq_file *seq, void *v) }; seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n", - GENL_MAGIC_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX, drbd_buildtag()); + DRBD_FAMILY_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX, drbd_buildtag()); /* cs .. connection state diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h deleted file mode 100644 index f53c534aba0c..000000000000 --- a/include/linux/drbd_genl.h +++ /dev/null @@ -1,536 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * General overview: - * full generic netlink message: - * |nlmsghdr|genlmsghdr| - * - * payload: - * |optional fixed size family header| - * - * sequence of netlink attributes: - * I chose to have all "top level" attributes NLA_NESTED, - * corresponding to some real struct. - * So we have a sequence of |tla, len| - * - * nested nla sequence: - * may be empty, or contain a sequence of netlink attributes - * representing the struct fields. - * - * The tag number of any field (regardless of containing struct) - * will be available as T_ ## field_name, - * so you cannot have the same field name in two differnt structs. - * - * The tag numbers themselves are per struct, though, - * so should always begin at 1 (not 0, that is the special "NLA_UNSPEC" type, - * which we won't use here). - * The tag numbers are used as index in the respective nla_policy array. - * - * GENL_struct(tag_name, tag_number, struct name, struct fields) - struct and policy - * genl_magic_struct.h - * generates the struct declaration, - * generates an entry in the tla enum, - * genl_magic_func.h - * generates an entry in the static tla policy - * with .type = NLA_NESTED - * generates the static _nl_policy definition, - * and static conversion functions - * - * genl_magic_func.h - * - * GENL_mc_group(group) - * genl_magic_struct.h - * does nothing - * genl_magic_func.h - * defines and registers the mcast group, - * and provides a send helper - * - * GENL_notification(op_name, op_num, mcast_group, tla list) - * These are notifications to userspace. - * - * genl_magic_struct.h - * generates an entry in the genl_ops enum, - * genl_magic_func.h - * does nothing - * - * mcast group: the name of the mcast group this notification should be - * expected on - * tla list: the list of expected top level attributes, - * for documentation and sanity checking. - * - * GENL_op(op_name, op_num, flags and handler, tla list) - "genl operations" - * These are requests from userspace. - * - * _op and _notification share the same "number space", - * op_nr will be assigned to "genlmsghdr->cmd" - * - * genl_magic_struct.h - * generates an entry in the genl_ops enum, - * genl_magic_func.h - * generates an entry in the static genl_ops array, - * and static register/unregister functions to - * genl_register_family(). - * - * flags and handler: - * GENL_op_init( .doit = x, .dumpit = y, .flags = something) - * GENL_doit(x) => .dumpit = NULL, .flags = GENL_ADMIN_PERM - * tla list: the list of expected top level attributes, - * for documentation and sanity checking. - */ - -/* - * STRUCTS - */ - -/* this is sent kernel -> userland on various error conditions, and contains - * informational textual info, which is supposedly human readable. - * The computer relevant return code is in the drbd_genlmsghdr. - */ -GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply, - /* "arbitrary" size strings, nla_policy.len = 0 */ - __str_field(1, 0, info_text, 0) -) - -/* Configuration requests typically need a context to operate on. - * Possible keys are device minor (fits in the drbd_genlmsghdr), - * the replication link (aka connection) name, - * and/or the replication group (aka resource) name, - * and the volume id within the resource. */ -GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context, - __u32_field(1, 0, ctx_volume) - __str_field(2, 0, ctx_resource_name, 128) - __bin_field(3, 0, ctx_my_addr, 128) - __bin_field(4, 0, ctx_peer_addr, 128) -) - -GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf, - __str_field(1, DRBD_F_REQUIRED | DRBD_F_INVARIANT, backing_dev, 128) - __str_field(2, DRBD_F_REQUIRED | DRBD_F_INVARIANT, meta_dev, 128) - __s32_field(3, DRBD_F_REQUIRED | DRBD_F_INVARIANT, meta_dev_idx) - - /* use the resize command to try and change the disk_size */ - __u64_field(4, DRBD_F_INVARIANT, disk_size) - /* we could change the max_bio_bvecs, - * but it won't propagate through the stack */ - __u32_field(5, DRBD_F_INVARIANT, max_bio_bvecs) - - __u32_field_def(6, 0, on_io_error, DRBD_ON_IO_ERROR_DEF) - __u32_field_def(7, 0, fencing, DRBD_FENCING_DEF) - - __u32_field_def(8, 0, resync_rate, DRBD_RESYNC_RATE_DEF) - __s32_field_def(9, 0, resync_after, DRBD_MINOR_NUMBER_DEF) - __u32_field_def(10, 0, al_extents, DRBD_AL_EXTENTS_DEF) - __u32_field_def(11, 0, c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF) - __u32_field_def(12, 0, c_delay_target, DRBD_C_DELAY_TARGET_DEF) - __u32_field_def(13, 0, c_fill_target, DRBD_C_FILL_TARGET_DEF) - __u32_field_def(14, 0, c_max_rate, DRBD_C_MAX_RATE_DEF) - __u32_field_def(15, 0, c_min_rate, DRBD_C_MIN_RATE_DEF) - __u32_field_def(20, 0, disk_timeout, DRBD_DISK_TIMEOUT_DEF) - __u32_field_def(21, 0 /* OPTIONAL */, read_balancing, DRBD_READ_BALANCING_DEF) - __u32_field_def(25, 0 /* OPTIONAL */, rs_discard_granularity, DRBD_RS_DISCARD_GRANULARITY_DEF) - - __flg_field_def(16, 0, disk_barrier, DRBD_DISK_BARRIER_DEF) - __flg_field_def(17, 0, disk_flushes, DRBD_DISK_FLUSHES_DEF) - __flg_field_def(18, 0, disk_drain, DRBD_DISK_DRAIN_DEF) - __flg_field_def(19, 0, md_flushes, DRBD_MD_FLUSHES_DEF) - __flg_field_def(23, 0 /* OPTIONAL */, al_updates, DRBD_AL_UPDATES_DEF) - __flg_field_def(24, 0 /* OPTIONAL */, discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF) - __flg_field_def(26, 0 /* OPTIONAL */, disable_write_same, DRBD_DISABLE_WRITE_SAME_DEF) -) - -GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts, - __str_field_def(1, 0, cpu_mask, DRBD_CPU_MASK_SIZE) - __u32_field_def(2, 0, on_no_data, DRBD_ON_NO_DATA_DEF) -) - -GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf, - __str_field_def(1, DRBD_F_SENSITIVE, - shared_secret, SHARED_SECRET_MAX) - __str_field_def(2, 0, cram_hmac_alg, SHARED_SECRET_MAX) - __str_field_def(3, 0, integrity_alg, SHARED_SECRET_MAX) - __str_field_def(4, 0, verify_alg, SHARED_SECRET_MAX) - __str_field_def(5, 0, csums_alg, SHARED_SECRET_MAX) - __u32_field_def(6, 0, wire_protocol, DRBD_PROTOCOL_DEF) - __u32_field_def(7, 0, connect_int, DRBD_CONNECT_INT_DEF) - __u32_field_def(8, 0, timeout, DRBD_TIMEOUT_DEF) - __u32_field_def(9, 0, ping_int, DRBD_PING_INT_DEF) - __u32_field_def(10, 0, ping_timeo, DRBD_PING_TIMEO_DEF) - __u32_field_def(11, 0, sndbuf_size, DRBD_SNDBUF_SIZE_DEF) - __u32_field_def(12, 0, rcvbuf_size, DRBD_RCVBUF_SIZE_DEF) - __u32_field_def(13, 0, ko_count, DRBD_KO_COUNT_DEF) - __u32_field_def(14, 0, max_buffers, DRBD_MAX_BUFFERS_DEF) - __u32_field_def(15, 0, max_epoch_size, DRBD_MAX_EPOCH_SIZE_DEF) - __u32_field_def(16, 0, unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF) - __u32_field_def(17, 0, after_sb_0p, DRBD_AFTER_SB_0P_DEF) - __u32_field_def(18, 0, after_sb_1p, DRBD_AFTER_SB_1P_DEF) - __u32_field_def(19, 0, after_sb_2p, DRBD_AFTER_SB_2P_DEF) - __u32_field_def(20, 0, rr_conflict, DRBD_RR_CONFLICT_DEF) - __u32_field_def(21, 0, on_congestion, DRBD_ON_CONGESTION_DEF) - __u32_field_def(22, 0, cong_fill, DRBD_CONG_FILL_DEF) - __u32_field_def(23, 0, cong_extents, DRBD_CONG_EXTENTS_DEF) - __flg_field_def(24, 0, two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF) - __flg_field(25, DRBD_F_INVARIANT, discard_my_data) - __flg_field_def(26, 0, tcp_cork, DRBD_TCP_CORK_DEF) - __flg_field_def(27, 0, always_asbp, DRBD_ALWAYS_ASBP_DEF) - __flg_field(28, DRBD_F_INVARIANT, tentative) - __flg_field_def(29, 0, use_rle, DRBD_USE_RLE_DEF) - /* 9: __u32_field_def(30, 0, fencing_policy, DRBD_FENCING_DEF) */ - /* 9: __str_field_def(31, 0, name, SHARED_SECRET_MAX) */ - /* 9: __u32_field(32, DRBD_F_REQUIRED | DRBD_F_INVARIANT, peer_node_id) */ - __flg_field_def(33, 0 /* OPTIONAL */, csums_after_crash_only, DRBD_CSUMS_AFTER_CRASH_ONLY_DEF) - __u32_field_def(34, 0 /* OPTIONAL */, sock_check_timeo, DRBD_SOCKET_CHECK_TIMEO_DEF) -) - -GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms, - __flg_field(1, 0, assume_uptodate) -) - -GENL_struct(DRBD_NLA_RESIZE_PARMS, 7, resize_parms, - __u64_field(1, 0, resize_size) - __flg_field(2, 0, resize_force) - __flg_field(3, 0, no_resync) - __u32_field_def(4, 0 /* OPTIONAL */, al_stripes, DRBD_AL_STRIPES_DEF) - __u32_field_def(5, 0 /* OPTIONAL */, al_stripe_size, DRBD_AL_STRIPE_SIZE_DEF) -) - -GENL_struct(DRBD_NLA_STATE_INFO, 8, state_info, - /* the reason of the broadcast, - * if this is an event triggered broadcast. */ - __u32_field(1, 0, sib_reason) - __u32_field(2, DRBD_F_REQUIRED, current_state) - __u64_field(3, 0, capacity) - __u64_field(4, 0, ed_uuid) - - /* These are for broadcast from after state change work. - * prev_state and new_state are from the moment the state change took - * place, new_state is not neccessarily the same as current_state, - * there may have been more state changes since. Which will be - * broadcasted soon, in their respective after state change work. */ - __u32_field(5, 0, prev_state) - __u32_field(6, 0, new_state) - - /* if we have a local disk: */ - __bin_field(7, 0, uuids, (UI_SIZE*sizeof(__u64))) - __u32_field(8, 0, disk_flags) - __u64_field(9, 0, bits_total) - __u64_field(10, 0, bits_oos) - /* and in case resync or online verify is active */ - __u64_field(11, 0, bits_rs_total) - __u64_field(12, 0, bits_rs_failed) - - /* for pre and post notifications of helper execution */ - __str_field(13, 0, helper, 32) - __u32_field(14, 0, helper_exit_code) - - __u64_field(15, 0, send_cnt) - __u64_field(16, 0, recv_cnt) - __u64_field(17, 0, read_cnt) - __u64_field(18, 0, writ_cnt) - __u64_field(19, 0, al_writ_cnt) - __u64_field(20, 0, bm_writ_cnt) - __u32_field(21, 0, ap_bio_cnt) - __u32_field(22, 0, ap_pending_cnt) - __u32_field(23, 0, rs_pending_cnt) -) - -GENL_struct(DRBD_NLA_START_OV_PARMS, 9, start_ov_parms, - __u64_field(1, 0, ov_start_sector) - __u64_field(2, 0, ov_stop_sector) -) - -GENL_struct(DRBD_NLA_NEW_C_UUID_PARMS, 10, new_c_uuid_parms, - __flg_field(1, 0, clear_bm) -) - -GENL_struct(DRBD_NLA_TIMEOUT_PARMS, 11, timeout_parms, - __u32_field(1, DRBD_F_REQUIRED, timeout_type) -) - -GENL_struct(DRBD_NLA_DISCONNECT_PARMS, 12, disconnect_parms, - __flg_field(1, 0, force_disconnect) -) - -GENL_struct(DRBD_NLA_DETACH_PARMS, 13, detach_parms, - __flg_field(1, 0, force_detach) -) - -GENL_struct(DRBD_NLA_RESOURCE_INFO, 15, resource_info, - __u32_field(1, 0, res_role) - __flg_field(2, 0, res_susp) - __flg_field(3, 0, res_susp_nod) - __flg_field(4, 0, res_susp_fen) - /* __flg_field(5, 0, res_weak) */ -) - -GENL_struct(DRBD_NLA_DEVICE_INFO, 16, device_info, - __u32_field(1, 0, dev_disk_state) -) - -GENL_struct(DRBD_NLA_CONNECTION_INFO, 17, connection_info, - __u32_field(1, 0, conn_connection_state) - __u32_field(2, 0, conn_role) -) - -GENL_struct(DRBD_NLA_PEER_DEVICE_INFO, 18, peer_device_info, - __u32_field(1, 0, peer_repl_state) - __u32_field(2, 0, peer_disk_state) - __u32_field(3, 0, peer_resync_susp_user) - __u32_field(4, 0, peer_resync_susp_peer) - __u32_field(5, 0, peer_resync_susp_dependency) -) - -GENL_struct(DRBD_NLA_RESOURCE_STATISTICS, 19, resource_statistics, - __u32_field(1, 0, res_stat_write_ordering) -) - -GENL_struct(DRBD_NLA_DEVICE_STATISTICS, 20, device_statistics, - __u64_field(1, 0, dev_size) /* (sectors) */ - __u64_field(2, 0, dev_read) /* (sectors) */ - __u64_field(3, 0, dev_write) /* (sectors) */ - __u64_field(4, 0, dev_al_writes) /* activity log writes (count) */ - __u64_field(5, 0, dev_bm_writes) /* bitmap writes (count) */ - __u32_field(6, 0, dev_upper_pending) /* application requests in progress */ - __u32_field(7, 0, dev_lower_pending) /* backing device requests in progress */ - __flg_field(8, 0, dev_upper_blocked) - __flg_field(9, 0, dev_lower_blocked) - __flg_field(10, 0, dev_al_suspended) /* activity log suspended */ - __u64_field(11, 0, dev_exposed_data_uuid) - __u64_field(12, 0, dev_current_uuid) - __u32_field(13, 0, dev_disk_flags) - __bin_field(14, 0, history_uuids, HISTORY_UUIDS * sizeof(__u64)) -) - -GENL_struct(DRBD_NLA_CONNECTION_STATISTICS, 21, connection_statistics, - __flg_field(1, 0, conn_congested) -) - -GENL_struct(DRBD_NLA_PEER_DEVICE_STATISTICS, 22, peer_device_statistics, - __u64_field(1, 0, peer_dev_received) /* sectors */ - __u64_field(2, 0, peer_dev_sent) /* sectors */ - __u32_field(3, 0, peer_dev_pending) /* number of requests */ - __u32_field(4, 0, peer_dev_unacked) /* number of requests */ - __u64_field(5, 0, peer_dev_out_of_sync) /* sectors */ - __u64_field(6, 0, peer_dev_resync_failed) /* sectors */ - __u64_field(7, 0, peer_dev_bitmap_uuid) - __u32_field(9, 0, peer_dev_flags) -) - -GENL_struct(DRBD_NLA_NOTIFICATION_HEADER, 23, drbd_notification_header, - __u32_field(1, 0, nh_type) -) - -GENL_struct(DRBD_NLA_HELPER, 24, drbd_helper_info, - __str_field(1, 0, helper_name, 32) - __u32_field(2, 0, helper_status) -) - -/* - * Notifications and commands (genlmsghdr->cmd) - */ -GENL_mc_group(events) - - /* kernel -> userspace announcement of changes */ -GENL_notification( - DRBD_EVENT, 1, events, - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_STATE_INFO, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_NET_CONF, 0) - GENL_tla_expected(DRBD_NLA_DISK_CONF, 0) - GENL_tla_expected(DRBD_NLA_SYNCER_CONF, 0) -) - - /* query kernel for specific or all info */ -GENL_op( - DRBD_ADM_GET_STATUS, 2, - GENL_op_init( - .doit = drbd_adm_get_status, - .dumpit = drbd_adm_get_status_all, - /* anyone may ask for the status, - * it is broadcasted anyways */ - ), - /* To select the object .doit. - * Or a subset of objects in .dumpit. */ - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, 0) -) - - /* add DRBD minor devices as volumes to resources */ -GENL_op(DRBD_ADM_NEW_MINOR, 5, GENL_doit(drbd_adm_new_minor), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_DEL_MINOR, 6, GENL_doit(drbd_adm_del_minor), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) - - /* add or delete resources */ -GENL_op(DRBD_ADM_NEW_RESOURCE, 7, GENL_doit(drbd_adm_new_resource), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_DEL_RESOURCE, 8, GENL_doit(drbd_adm_del_resource), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) - -GENL_op(DRBD_ADM_RESOURCE_OPTS, 9, - GENL_doit(drbd_adm_resource_opts), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_RESOURCE_OPTS, 0) -) - -GENL_op( - DRBD_ADM_CONNECT, 10, - GENL_doit(drbd_adm_connect), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_F_REQUIRED) -) - -GENL_op( - DRBD_ADM_CHG_NET_OPTS, 29, - GENL_doit(drbd_adm_net_opts), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_F_REQUIRED) -) - -GENL_op(DRBD_ADM_DISCONNECT, 11, GENL_doit(drbd_adm_disconnect), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) - -GENL_op(DRBD_ADM_ATTACH, 12, - GENL_doit(drbd_adm_attach), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_DISK_CONF, DRBD_F_REQUIRED) -) - -GENL_op(DRBD_ADM_CHG_DISK_OPTS, 28, - GENL_doit(drbd_adm_disk_opts), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_DISK_OPTS, DRBD_F_REQUIRED) -) - -GENL_op( - DRBD_ADM_RESIZE, 13, - GENL_doit(drbd_adm_resize), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_RESIZE_PARMS, 0) -) - -GENL_op( - DRBD_ADM_PRIMARY, 14, - GENL_doit(drbd_adm_set_role), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, DRBD_F_REQUIRED) -) - -GENL_op( - DRBD_ADM_SECONDARY, 15, - GENL_doit(drbd_adm_set_role), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, DRBD_F_REQUIRED) -) - -GENL_op( - DRBD_ADM_NEW_C_UUID, 16, - GENL_doit(drbd_adm_new_c_uuid), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_NEW_C_UUID_PARMS, 0) -) - -GENL_op( - DRBD_ADM_START_OV, 17, - GENL_doit(drbd_adm_start_ov), - GENL_tla_expected(DRBD_NLA_START_OV_PARMS, 0) -) - -GENL_op(DRBD_ADM_DETACH, 18, GENL_doit(drbd_adm_detach), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_DETACH_PARMS, 0)) - -GENL_op(DRBD_ADM_INVALIDATE, 19, GENL_doit(drbd_adm_invalidate), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_INVAL_PEER, 20, GENL_doit(drbd_adm_invalidate_peer), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_PAUSE_SYNC, 21, GENL_doit(drbd_adm_pause_sync), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_RESUME_SYNC, 22, GENL_doit(drbd_adm_resume_sync), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_SUSPEND_IO, 23, GENL_doit(drbd_adm_suspend_io), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_RESUME_IO, 24, GENL_doit(drbd_adm_resume_io), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_OUTDATE, 25, GENL_doit(drbd_adm_outdate), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_GET_TIMEOUT_TYPE, 26, GENL_doit(drbd_adm_get_timeout_type), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) -GENL_op(DRBD_ADM_DOWN, 27, GENL_doit(drbd_adm_down), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) - -GENL_op(DRBD_ADM_GET_RESOURCES, 30, - GENL_op_init( - .dumpit = drbd_adm_dump_resources, - ), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, 0) - GENL_tla_expected(DRBD_NLA_RESOURCE_INFO, 0) - GENL_tla_expected(DRBD_NLA_RESOURCE_STATISTICS, 0)) - -GENL_op(DRBD_ADM_GET_DEVICES, 31, - GENL_op_init( - .dumpit = drbd_adm_dump_devices, - .done = drbd_adm_dump_devices_done, - ), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, 0) - GENL_tla_expected(DRBD_NLA_DEVICE_INFO, 0) - GENL_tla_expected(DRBD_NLA_DEVICE_STATISTICS, 0)) - -GENL_op(DRBD_ADM_GET_CONNECTIONS, 32, - GENL_op_init( - .dumpit = drbd_adm_dump_connections, - .done = drbd_adm_dump_connections_done, - ), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, 0) - GENL_tla_expected(DRBD_NLA_CONNECTION_INFO, 0) - GENL_tla_expected(DRBD_NLA_CONNECTION_STATISTICS, 0)) - -GENL_op(DRBD_ADM_GET_PEER_DEVICES, 33, - GENL_op_init( - .dumpit = drbd_adm_dump_peer_devices, - .done = drbd_adm_dump_peer_devices_done, - ), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, 0) - GENL_tla_expected(DRBD_NLA_PEER_DEVICE_INFO, 0) - GENL_tla_expected(DRBD_NLA_PEER_DEVICE_STATISTICS, 0)) - -GENL_notification( - DRBD_RESOURCE_STATE, 34, events, - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_RESOURCE_INFO, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_RESOURCE_STATISTICS, DRBD_F_REQUIRED)) - -GENL_notification( - DRBD_DEVICE_STATE, 35, events, - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_DEVICE_INFO, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_DEVICE_STATISTICS, DRBD_F_REQUIRED)) - -GENL_notification( - DRBD_CONNECTION_STATE, 36, events, - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_CONNECTION_INFO, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_CONNECTION_STATISTICS, DRBD_F_REQUIRED)) - -GENL_notification( - DRBD_PEER_DEVICE_STATE, 37, events, - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_PEER_DEVICE_INFO, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_PEER_DEVICE_STATISTICS, DRBD_F_REQUIRED)) - -GENL_op( - DRBD_ADM_GET_INITIAL_STATE, 38, - GENL_op_init( - .dumpit = drbd_adm_get_initial_state, - ), - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, 0)) - -GENL_notification( - DRBD_HELPER, 40, events, - GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) - GENL_tla_expected(DRBD_NLA_HELPER, DRBD_F_REQUIRED)) - -GENL_notification( - DRBD_INITIAL_STATE_DONE, 41, events, - GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)) diff --git a/include/linux/drbd_genl_api.h b/include/linux/drbd_genl_api.h deleted file mode 100644 index 19d263924852..000000000000 --- a/include/linux/drbd_genl_api.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef DRBD_GENL_STRUCT_H -#define DRBD_GENL_STRUCT_H - -/* hack around predefined gcc/cpp "linux=1", - * we cannot possibly include <1/drbd_genl.h> */ -#undef linux - -#include -#define GENL_MAGIC_VERSION 1 -#define GENL_MAGIC_FAMILY drbd -#define GENL_MAGIC_FAMILY_HDRSZ sizeof(struct drbd_genlmsghdr) -#define GENL_MAGIC_INCLUDE_FILE -#include - -#endif diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h deleted file mode 100644 index a7d36c9ea924..000000000000 --- a/include/linux/genl_magic_func.h +++ /dev/null @@ -1,413 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef GENL_MAGIC_FUNC_H -#define GENL_MAGIC_FUNC_H - -#include -#include -#include - -/* - * Magic: declare tla policy {{{1 - * Magic: declare nested policies - * {{{2 - */ -#undef GENL_mc_group -#define GENL_mc_group(group) - -#undef GENL_notification -#define GENL_notification(op_name, op_num, mcast_group, tla_list) - -#undef GENL_op -#define GENL_op(op_name, op_num, handler, tla_list) - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ - [tag_name] = { .type = NLA_NESTED }, - -static struct nla_policy CONCATENATE(GENL_MAGIC_FAMILY, _tla_nl_policy)[] = { -#include GENL_MAGIC_INCLUDE_FILE -}; - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ -static struct nla_policy s_name ## _nl_policy[] __read_mostly = \ -{ s_fields }; - -#undef __field -#define __field(attr_nr, attr_flag, name, nla_type, _type, __get, \ - __put, __is_signed) \ - [attr_nr] = { .type = nla_type }, - -#undef __array -#define __array(attr_nr, attr_flag, name, nla_type, _type, maxlen, \ - __get, __put, __is_signed) \ - [attr_nr] = { .type = nla_type, \ - .len = maxlen - (nla_type == NLA_NUL_STRING) }, - -#include GENL_MAGIC_INCLUDE_FILE - -#ifndef __KERNEL__ -#ifndef pr_info -#define pr_info(args...) fprintf(stderr, args); -#endif -#endif - -#ifdef GENL_MAGIC_DEBUG -static void dprint_field(const char *dir, int nla_type, - const char *name, void *valp) -{ - __u64 val = valp ? *(__u32 *)valp : 1; - switch (nla_type) { - case NLA_U8: val = (__u8)val; - case NLA_U16: val = (__u16)val; - case NLA_U32: val = (__u32)val; - pr_info("%s attr %s: %d 0x%08x\n", dir, - name, (int)val, (unsigned)val); - break; - case NLA_U64: - val = *(__u64*)valp; - pr_info("%s attr %s: %lld 0x%08llx\n", dir, - name, (long long)val, (unsigned long long)val); - break; - case NLA_FLAG: - if (val) - pr_info("%s attr %s: set\n", dir, name); - break; - } -} - -static void dprint_array(const char *dir, int nla_type, - const char *name, const char *val, unsigned len) -{ - switch (nla_type) { - case NLA_NUL_STRING: - if (len && val[len-1] == '\0') - len--; - pr_info("%s attr %s: [len:%u] '%s'\n", dir, name, len, val); - break; - default: - /* we can always show 4 byte, - * thats what nlattr are aligned to. */ - pr_info("%s attr %s: [len:%u] %02x%02x%02x%02x ...\n", - dir, name, len, val[0], val[1], val[2], val[3]); - } -} - -#define DPRINT_TLA(a, op, b) pr_info("%s %s %s\n", a, op, b); - -/* Name is a member field name of the struct s. - * If s is NULL (only parsing, no copy requested in *_from_attrs()), - * nla is supposed to point to the attribute containing the information - * corresponding to that struct member. */ -#define DPRINT_FIELD(dir, nla_type, name, s, nla) \ - do { \ - if (s) \ - dprint_field(dir, nla_type, #name, &s->name); \ - else if (nla) \ - dprint_field(dir, nla_type, #name, \ - (nla_type == NLA_FLAG) ? NULL \ - : nla_data(nla)); \ - } while (0) - -#define DPRINT_ARRAY(dir, nla_type, name, s, nla) \ - do { \ - if (s) \ - dprint_array(dir, nla_type, #name, \ - s->name, s->name ## _len); \ - else if (nla) \ - dprint_array(dir, nla_type, #name, \ - nla_data(nla), nla_len(nla)); \ - } while (0) -#else -#define DPRINT_TLA(a, op, b) do {} while (0) -#define DPRINT_FIELD(dir, nla_type, name, s, nla) do {} while (0) -#define DPRINT_ARRAY(dir, nla_type, name, s, nla) do {} while (0) -#endif - -/* - * Magic: provide conversion functions {{{1 - * populate struct from attribute table: - * {{{2 - */ - -/* processing of generic netlink messages is serialized. - * use one static buffer for parsing of nested attributes */ -static struct nlattr *nested_attr_tb[128]; - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ -/* *_from_attrs functions are static, but potentially unused */ \ -static int __ ## s_name ## _from_attrs(struct s_name *s, \ - struct genl_info *info, bool exclude_invariants) \ -{ \ - const int maxtype = ARRAY_SIZE(s_name ## _nl_policy)-1; \ - struct nlattr *tla = info->attrs[tag_number]; \ - struct nlattr **ntb = nested_attr_tb; \ - struct nlattr *nla; \ - int err; \ - BUILD_BUG_ON(ARRAY_SIZE(s_name ## _nl_policy) > ARRAY_SIZE(nested_attr_tb)); \ - if (!tla) \ - return -ENOMSG; \ - DPRINT_TLA(#s_name, "<=-", #tag_name); \ - err = nla_parse_nested_deprecated(ntb, maxtype, tla, \ - s_name ## _nl_policy, NULL); \ - if (err) \ - return err; \ - \ - s_fields \ - return 0; \ -} __attribute__((unused)) \ -static int s_name ## _from_attrs(struct s_name *s, \ - struct genl_info *info) \ -{ \ - return __ ## s_name ## _from_attrs(s, info, false); \ -} __attribute__((unused)) \ -static int s_name ## _from_attrs_for_change(struct s_name *s, \ - struct genl_info *info) \ -{ \ - return __ ## s_name ## _from_attrs(s, info, true); \ -} __attribute__((unused)) \ - -#define __assign(attr_nr, attr_flag, name, nla_type, type, assignment...) \ - nla = ntb[attr_nr]; \ - if (nla) { \ - if (exclude_invariants && !!((attr_flag) & DRBD_F_INVARIANT)) { \ - pr_info("<< must not change invariant attr: %s\n", #name); \ - return -EEXIST; \ - } \ - assignment; \ - } else if (exclude_invariants && !!((attr_flag) & DRBD_F_INVARIANT)) { \ - /* attribute missing from payload, */ \ - /* which was expected */ \ - } else if ((attr_flag) & DRBD_F_REQUIRED) { \ - pr_info("<< missing attr: %s\n", #name); \ - return -ENOMSG; \ - } - -#undef __field -#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ - __is_signed) \ - __assign(attr_nr, attr_flag, name, nla_type, type, \ - if (s) \ - s->name = __get(nla); \ - DPRINT_FIELD("<<", nla_type, name, s, nla)) - -/* validate_nla() already checked nla_len <= maxlen appropriately. */ -#undef __array -#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ - __get, __put, __is_signed) \ - __assign(attr_nr, attr_flag, name, nla_type, type, \ - if (s) \ - s->name ## _len = \ - __get(s->name, nla, maxlen); \ - DPRINT_ARRAY("<<", nla_type, name, s, nla)) - -#include GENL_MAGIC_INCLUDE_FILE - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) - -/* - * Magic: define op number to op name mapping {{{1 - * {{{2 - */ -static const char *CONCATENATE(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd) -{ - switch (cmd) { -#undef GENL_op -#define GENL_op(op_name, op_num, handler, tla_list) \ - case op_num: return #op_name; -#include GENL_MAGIC_INCLUDE_FILE - default: - return "unknown"; - } -} - -#ifdef __KERNEL__ -#include -/* - * Magic: define genl_ops {{{1 - * {{{2 - */ - -#undef GENL_op -#define GENL_op(op_name, op_num, handler, tla_list) \ -{ \ - handler \ - .cmd = op_name, \ -}, - -#define ZZZ_genl_ops CONCATENATE(GENL_MAGIC_FAMILY, _genl_ops) -static struct genl_ops ZZZ_genl_ops[] __read_mostly = { -#include GENL_MAGIC_INCLUDE_FILE -}; - -#undef GENL_op -#define GENL_op(op_name, op_num, handler, tla_list) - -/* - * Define the genl_family, multicast groups, {{{1 - * and provide register/unregister functions. - * {{{2 - */ -#define ZZZ_genl_family CONCATENATE(GENL_MAGIC_FAMILY, _genl_family) -static struct genl_family ZZZ_genl_family; -/* - * Magic: define multicast groups - * Magic: define multicast group registration helper - */ -#define ZZZ_genl_mcgrps CONCATENATE(GENL_MAGIC_FAMILY, _genl_mcgrps) -static const struct genl_multicast_group ZZZ_genl_mcgrps[] = { -#undef GENL_mc_group -#define GENL_mc_group(group) { .name = #group, }, -#include GENL_MAGIC_INCLUDE_FILE -}; - -enum CONCATENATE(GENL_MAGIC_FAMILY, group_ids) { -#undef GENL_mc_group -#define GENL_mc_group(group) CONCATENATE(GENL_MAGIC_FAMILY, _group_ ## group), -#include GENL_MAGIC_INCLUDE_FILE -}; - -#undef GENL_mc_group -#define GENL_mc_group(group) \ -static int CONCATENATE(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)( \ - struct sk_buff *skb, gfp_t flags) \ -{ \ - unsigned int group_id = \ - CONCATENATE(GENL_MAGIC_FAMILY, _group_ ## group); \ - return genlmsg_multicast(&ZZZ_genl_family, skb, 0, \ - group_id, flags); \ -} - -#include GENL_MAGIC_INCLUDE_FILE - -#undef GENL_mc_group -#define GENL_mc_group(group) - -static struct genl_family ZZZ_genl_family __ro_after_init = { - .name = __stringify(GENL_MAGIC_FAMILY), - .version = GENL_MAGIC_VERSION, -#ifdef GENL_MAGIC_FAMILY_HDRSZ - .hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ), -#endif - .maxattr = ARRAY_SIZE(CONCATENATE(GENL_MAGIC_FAMILY, _tla_nl_policy))-1, - .policy = CONCATENATE(GENL_MAGIC_FAMILY, _tla_nl_policy), -#ifdef GENL_MAGIC_FAMILY_PRE_DOIT - .pre_doit = GENL_MAGIC_FAMILY_PRE_DOIT, - .post_doit = GENL_MAGIC_FAMILY_POST_DOIT, -#endif - .ops = ZZZ_genl_ops, - .n_ops = ARRAY_SIZE(ZZZ_genl_ops), - .mcgrps = ZZZ_genl_mcgrps, - .resv_start_op = 42, /* drbd is currently the only user */ - .n_mcgrps = ARRAY_SIZE(ZZZ_genl_mcgrps), - .module = THIS_MODULE, -}; - -int CONCATENATE(GENL_MAGIC_FAMILY, _genl_register)(void) -{ - return genl_register_family(&ZZZ_genl_family); -} - -void CONCATENATE(GENL_MAGIC_FAMILY, _genl_unregister)(void) -{ - genl_unregister_family(&ZZZ_genl_family); -} - -/* - * Magic: provide conversion functions {{{1 - * populate skb from struct. - * {{{2 - */ - -#undef GENL_op -#define GENL_op(op_name, op_num, handler, tla_list) - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ -static int s_name ## _to_skb(struct sk_buff *skb, struct s_name *s, \ - const bool exclude_sensitive) \ -{ \ - struct nlattr *tla = nla_nest_start(skb, tag_number); \ - if (!tla) \ - goto nla_put_failure; \ - DPRINT_TLA(#s_name, "-=>", #tag_name); \ - s_fields \ - nla_nest_end(skb, tla); \ - return 0; \ - \ -nla_put_failure: \ - if (tla) \ - nla_nest_cancel(skb, tla); \ - return -EMSGSIZE; \ -} \ -static inline int s_name ## _to_priv_skb(struct sk_buff *skb, \ - struct s_name *s) \ -{ \ - return s_name ## _to_skb(skb, s, 0); \ -} \ -static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb, \ - struct s_name *s) \ -{ \ - return s_name ## _to_skb(skb, s, 1); \ -} - - -#undef __field -#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ - __is_signed) \ - if (!exclude_sensitive || !((attr_flag) & DRBD_F_SENSITIVE)) { \ - DPRINT_FIELD(">>", nla_type, name, s, NULL); \ - if (__put(skb, attr_nr, s->name)) \ - goto nla_put_failure; \ - } - -#undef __array -#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ - __get, __put, __is_signed) \ - if (!exclude_sensitive || !((attr_flag) & DRBD_F_SENSITIVE)) { \ - DPRINT_ARRAY(">>",nla_type, name, s, NULL); \ - if (__put(skb, attr_nr, min_t(int, maxlen, \ - s->name ## _len + (nla_type == NLA_NUL_STRING)),\ - s->name)) \ - goto nla_put_failure; \ - } - -#include GENL_MAGIC_INCLUDE_FILE - - -/* Functions for initializing structs to default values. */ - -#undef __field -#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ - __is_signed) -#undef __array -#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ - __get, __put, __is_signed) -#undef __u32_field_def -#define __u32_field_def(attr_nr, attr_flag, name, default) \ - x->name = default; -#undef __s32_field_def -#define __s32_field_def(attr_nr, attr_flag, name, default) \ - x->name = default; -#undef __flg_field_def -#define __flg_field_def(attr_nr, attr_flag, name, default) \ - x->name = default; -#undef __str_field_def -#define __str_field_def(attr_nr, attr_flag, name, maxlen) \ - memset(x->name, 0, sizeof(x->name)); \ - x->name ## _len = 0; -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ -static void set_ ## s_name ## _defaults(struct s_name *x) __attribute__((unused)); \ -static void set_ ## s_name ## _defaults(struct s_name *x) { \ -s_fields \ -} - -#include GENL_MAGIC_INCLUDE_FILE - -#endif /* __KERNEL__ */ - -/* }}}1 */ -#endif /* GENL_MAGIC_FUNC_H */ diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h deleted file mode 100644 index 2200cedd160a..000000000000 --- a/include/linux/genl_magic_struct.h +++ /dev/null @@ -1,272 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef GENL_MAGIC_STRUCT_H -#define GENL_MAGIC_STRUCT_H - -#ifndef GENL_MAGIC_FAMILY -# error "you need to define GENL_MAGIC_FAMILY before inclusion" -#endif - -#ifndef GENL_MAGIC_VERSION -# error "you need to define GENL_MAGIC_VERSION before inclusion" -#endif - -#ifndef GENL_MAGIC_INCLUDE_FILE -# error "you need to define GENL_MAGIC_INCLUDE_FILE before inclusion" -#endif - -#include -#include -#include - -extern int CONCATENATE(GENL_MAGIC_FAMILY, _genl_register)(void); -extern void CONCATENATE(GENL_MAGIC_FAMILY, _genl_unregister)(void); - -/* - * Extension of genl attribute validation policies {{{2 - */ - -/* - * Flags specific to drbd and not visible at the netlink layer, used in - * _from_attrs and _to_skb: - * - * @DRBD_F_REQUIRED: Attribute is required; a request without this attribute is - * invalid. - * - * @DRBD_F_SENSITIVE: Attribute includes sensitive information and must not be - * included in unpriviledged get requests or broadcasts. - * - * @DRBD_F_INVARIANT: Attribute is set when an object is initially created, but - * cannot subsequently be changed. - */ -#define DRBD_F_REQUIRED (1 << 0) -#define DRBD_F_SENSITIVE (1 << 1) -#define DRBD_F_INVARIANT (1 << 2) - - -/* }}}1 - * MAGIC - * multi-include macro expansion magic starts here - */ - -/* MAGIC helpers {{{2 */ - -static inline int nla_put_u64_0pad(struct sk_buff *skb, int attrtype, u64 value) -{ - return nla_put_64bit(skb, attrtype, sizeof(u64), &value, 0); -} - -/* possible field types */ -#define __flg_field(attr_nr, attr_flag, name) \ - __field(attr_nr, attr_flag, name, NLA_U8, char, \ - nla_get_u8, nla_put_u8, false) -#define __u8_field(attr_nr, attr_flag, name) \ - __field(attr_nr, attr_flag, name, NLA_U8, unsigned char, \ - nla_get_u8, nla_put_u8, false) -#define __u16_field(attr_nr, attr_flag, name) \ - __field(attr_nr, attr_flag, name, NLA_U16, __u16, \ - nla_get_u16, nla_put_u16, false) -#define __u32_field(attr_nr, attr_flag, name) \ - __field(attr_nr, attr_flag, name, NLA_U32, __u32, \ - nla_get_u32, nla_put_u32, false) -#define __s32_field(attr_nr, attr_flag, name) \ - __field(attr_nr, attr_flag, name, NLA_U32, __s32, \ - nla_get_u32, nla_put_u32, true) -#define __u64_field(attr_nr, attr_flag, name) \ - __field(attr_nr, attr_flag, name, NLA_U64, __u64, \ - nla_get_u64, nla_put_u64_0pad, false) -#define __str_field(attr_nr, attr_flag, name, maxlen) \ - __array(attr_nr, attr_flag, name, NLA_NUL_STRING, char, maxlen, \ - nla_strscpy, nla_put, false) -#define __bin_field(attr_nr, attr_flag, name, maxlen) \ - __array(attr_nr, attr_flag, name, NLA_BINARY, char, maxlen, \ - nla_memcpy, nla_put, false) - -/* fields with default values */ -#define __flg_field_def(attr_nr, attr_flag, name, default) \ - __flg_field(attr_nr, attr_flag, name) -#define __u32_field_def(attr_nr, attr_flag, name, default) \ - __u32_field(attr_nr, attr_flag, name) -#define __s32_field_def(attr_nr, attr_flag, name, default) \ - __s32_field(attr_nr, attr_flag, name) -#define __str_field_def(attr_nr, attr_flag, name, maxlen) \ - __str_field(attr_nr, attr_flag, name, maxlen) - -#define GENL_op_init(args...) args -#define GENL_doit(handler) \ - .doit = handler, \ - .flags = GENL_ADMIN_PERM, -#define GENL_dumpit(handler) \ - .dumpit = handler, \ - .flags = GENL_ADMIN_PERM, - -/* }}}1 - * Magic: define the enum symbols for genl_ops - * Magic: define the enum symbols for top level attributes - * Magic: define the enum symbols for nested attributes - * {{{2 - */ - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) - -#undef GENL_mc_group -#define GENL_mc_group(group) - -#undef GENL_notification -#define GENL_notification(op_name, op_num, mcast_group, tla_list) \ - op_name = op_num, - -#undef GENL_op -#define GENL_op(op_name, op_num, handler, tla_list) \ - op_name = op_num, - -enum { -#include GENL_MAGIC_INCLUDE_FILE -}; - -#undef GENL_notification -#define GENL_notification(op_name, op_num, mcast_group, tla_list) - -#undef GENL_op -#define GENL_op(op_name, op_num, handler, attr_list) - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ - tag_name = tag_number, - -enum { -#include GENL_MAGIC_INCLUDE_FILE -}; - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ -enum { \ - s_fields \ -}; - -#undef __field -#define __field(attr_nr, attr_flag, name, nla_type, type, \ - __get, __put, __is_signed) \ - T_ ## name = (__u16)(attr_nr), - -#undef __array -#define __array(attr_nr, attr_flag, name, nla_type, type, \ - maxlen, __get, __put, __is_signed) \ - T_ ## name = (__u16)(attr_nr), - -#include GENL_MAGIC_INCLUDE_FILE - -/* }}}1 - * Magic: compile time assert unique numbers for operations - * Magic: -"- unique numbers for top level attributes - * Magic: -"- unique numbers for nested attributes - * {{{2 - */ - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) - -#undef GENL_op -#define GENL_op(op_name, op_num, handler, attr_list) \ - case op_name: - -#undef GENL_notification -#define GENL_notification(op_name, op_num, mcast_group, tla_list) \ - case op_name: - -static inline void ct_assert_unique_operations(void) -{ - switch (0) { -#include GENL_MAGIC_INCLUDE_FILE - case 0: - ; - } -} - -#undef GENL_op -#define GENL_op(op_name, op_num, handler, attr_list) - -#undef GENL_notification -#define GENL_notification(op_name, op_num, mcast_group, tla_list) - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ - case tag_number: - -static inline void ct_assert_unique_top_level_attributes(void) -{ - switch (0) { -#include GENL_MAGIC_INCLUDE_FILE - case 0: - ; - } -} - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ -static inline void ct_assert_unique_ ## s_name ## _attributes(void) \ -{ \ - switch (0) { \ - s_fields \ - case 0: \ - ; \ - } \ -} - -#undef __field -#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ - __is_signed) \ - case attr_nr: - -#undef __array -#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ - __get, __put, __is_signed) \ - case attr_nr: - -#include GENL_MAGIC_INCLUDE_FILE - -/* }}}1 - * Magic: declare structs - * struct { - * fields - * }; - * {{{2 - */ - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ -struct s_name { s_fields }; - -#undef __field -#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ - __is_signed) \ - type name; - -#undef __array -#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ - __get, __put, __is_signed) \ - type name[maxlen]; \ - __u32 name ## _len; - -#include GENL_MAGIC_INCLUDE_FILE - -#undef GENL_struct -#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ -enum { \ - s_fields \ -}; - -#undef __field -#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ - is_signed) \ - F_ ## name ## _IS_SIGNED = is_signed, - -#undef __array -#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ - __get, __put, is_signed) \ - F_ ## name ## _IS_SIGNED = is_signed, - -#include GENL_MAGIC_INCLUDE_FILE - -/* }}}1 */ -#endif /* GENL_MAGIC_STRUCT_H */ diff --git a/include/uapi/linux/drbd.h b/include/uapi/linux/drbd.h index 7930a972d8a4..5d4d677cf1ad 100644 --- a/include/uapi/linux/drbd.h +++ b/include/uapi/linux/drbd.h @@ -333,6 +333,9 @@ enum drbd_uuid_index { #define HISTORY_UUIDS MAX_PEERS +#define DRBD_NL_UUIDS_SIZE (UI_SIZE * sizeof(__u64)) +#define DRBD_NL_HISTORY_UUIDS_SIZE (HISTORY_UUIDS * sizeof(__u64)) + enum drbd_timeout_flag { UT_DEFAULT = 0, UT_DEGRADED = 1, diff --git a/include/uapi/linux/drbd_genl.h b/include/uapi/linux/drbd_genl.h new file mode 100644 index 000000000000..8b25f08d8a90 --- /dev/null +++ b/include/uapi/linux/drbd_genl.h @@ -0,0 +1,359 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ + +#ifndef _UAPI_LINUX_DRBD_GENL_H +#define _UAPI_LINUX_DRBD_GENL_H + +#define DRBD_FAMILY_NAME "drbd" +#define DRBD_FAMILY_VERSION 1 + +enum { + DRBD_NLA_CFG_REPLY = 1, + DRBD_NLA_CFG_CONTEXT, + DRBD_NLA_DISK_CONF, + DRBD_NLA_RESOURCE_OPTS, + DRBD_NLA_NET_CONF, + DRBD_NLA_SET_ROLE_PARMS, + DRBD_NLA_RESIZE_PARMS, + DRBD_NLA_STATE_INFO, + DRBD_NLA_START_OV_PARMS, + DRBD_NLA_NEW_C_UUID_PARMS, + DRBD_NLA_TIMEOUT_PARMS, + DRBD_NLA_DISCONNECT_PARMS, + DRBD_NLA_DETACH_PARMS, + DRBD_NLA_RESOURCE_INFO = 15, + DRBD_NLA_DEVICE_INFO, + DRBD_NLA_CONNECTION_INFO, + DRBD_NLA_PEER_DEVICE_INFO, + DRBD_NLA_RESOURCE_STATISTICS, + DRBD_NLA_DEVICE_STATISTICS, + DRBD_NLA_CONNECTION_STATISTICS, + DRBD_NLA_PEER_DEVICE_STATISTICS, + DRBD_NLA_NOTIFICATION_HEADER, + DRBD_NLA_HELPER, + + __DRBD_NLA_MAX, + DRBD_NLA_MAX = (__DRBD_NLA_MAX - 1) +}; + +enum { + DRBD_A_DRBD_CFG_REPLY_INFO_TEXT = 1, + + __DRBD_A_DRBD_CFG_REPLY_MAX, + DRBD_A_DRBD_CFG_REPLY_MAX = (__DRBD_A_DRBD_CFG_REPLY_MAX - 1) +}; + +enum { + DRBD_A_DRBD_CFG_CONTEXT_CTX_VOLUME = 1, + DRBD_A_DRBD_CFG_CONTEXT_CTX_RESOURCE_NAME, + DRBD_A_DRBD_CFG_CONTEXT_CTX_MY_ADDR, + DRBD_A_DRBD_CFG_CONTEXT_CTX_PEER_ADDR, + + __DRBD_A_DRBD_CFG_CONTEXT_MAX, + DRBD_A_DRBD_CFG_CONTEXT_MAX = (__DRBD_A_DRBD_CFG_CONTEXT_MAX - 1) +}; + +enum { + DRBD_A_DISK_CONF_BACKING_DEV = 1, + DRBD_A_DISK_CONF_META_DEV, + DRBD_A_DISK_CONF_META_DEV_IDX, + DRBD_A_DISK_CONF_DISK_SIZE, + DRBD_A_DISK_CONF_MAX_BIO_BVECS, + DRBD_A_DISK_CONF_ON_IO_ERROR, + DRBD_A_DISK_CONF_FENCING, + DRBD_A_DISK_CONF_RESYNC_RATE, + DRBD_A_DISK_CONF_RESYNC_AFTER, + DRBD_A_DISK_CONF_AL_EXTENTS, + DRBD_A_DISK_CONF_C_PLAN_AHEAD, + DRBD_A_DISK_CONF_C_DELAY_TARGET, + DRBD_A_DISK_CONF_C_FILL_TARGET, + DRBD_A_DISK_CONF_C_MAX_RATE, + DRBD_A_DISK_CONF_C_MIN_RATE, + DRBD_A_DISK_CONF_DISK_BARRIER, + DRBD_A_DISK_CONF_DISK_FLUSHES, + DRBD_A_DISK_CONF_DISK_DRAIN, + DRBD_A_DISK_CONF_MD_FLUSHES, + DRBD_A_DISK_CONF_DISK_TIMEOUT, + DRBD_A_DISK_CONF_READ_BALANCING, + DRBD_A_DISK_CONF_AL_UPDATES = 23, + DRBD_A_DISK_CONF_DISCARD_ZEROES_IF_ALIGNED, + DRBD_A_DISK_CONF_RS_DISCARD_GRANULARITY, + DRBD_A_DISK_CONF_DISABLE_WRITE_SAME, + + __DRBD_A_DISK_CONF_MAX, + DRBD_A_DISK_CONF_MAX = (__DRBD_A_DISK_CONF_MAX - 1) +}; + +enum { + DRBD_A_RES_OPTS_CPU_MASK = 1, + DRBD_A_RES_OPTS_ON_NO_DATA, + + __DRBD_A_RES_OPTS_MAX, + DRBD_A_RES_OPTS_MAX = (__DRBD_A_RES_OPTS_MAX - 1) +}; + +enum { + DRBD_A_NET_CONF_SHARED_SECRET = 1, + DRBD_A_NET_CONF_CRAM_HMAC_ALG, + DRBD_A_NET_CONF_INTEGRITY_ALG, + DRBD_A_NET_CONF_VERIFY_ALG, + DRBD_A_NET_CONF_CSUMS_ALG, + DRBD_A_NET_CONF_WIRE_PROTOCOL, + DRBD_A_NET_CONF_CONNECT_INT, + DRBD_A_NET_CONF_TIMEOUT, + DRBD_A_NET_CONF_PING_INT, + DRBD_A_NET_CONF_PING_TIMEO, + DRBD_A_NET_CONF_SNDBUF_SIZE, + DRBD_A_NET_CONF_RCVBUF_SIZE, + DRBD_A_NET_CONF_KO_COUNT, + DRBD_A_NET_CONF_MAX_BUFFERS, + DRBD_A_NET_CONF_MAX_EPOCH_SIZE, + DRBD_A_NET_CONF_UNPLUG_WATERMARK, + DRBD_A_NET_CONF_AFTER_SB_0P, + DRBD_A_NET_CONF_AFTER_SB_1P, + DRBD_A_NET_CONF_AFTER_SB_2P, + DRBD_A_NET_CONF_RR_CONFLICT, + DRBD_A_NET_CONF_ON_CONGESTION, + DRBD_A_NET_CONF_CONG_FILL, + DRBD_A_NET_CONF_CONG_EXTENTS, + DRBD_A_NET_CONF_TWO_PRIMARIES, + DRBD_A_NET_CONF_DISCARD_MY_DATA, + DRBD_A_NET_CONF_TCP_CORK, + DRBD_A_NET_CONF_ALWAYS_ASBP, + DRBD_A_NET_CONF_TENTATIVE, + DRBD_A_NET_CONF_USE_RLE, + DRBD_A_NET_CONF_CSUMS_AFTER_CRASH_ONLY = 33, + DRBD_A_NET_CONF_SOCK_CHECK_TIMEO, + + __DRBD_A_NET_CONF_MAX, + DRBD_A_NET_CONF_MAX = (__DRBD_A_NET_CONF_MAX - 1) +}; + +enum { + DRBD_A_SET_ROLE_PARMS_ASSUME_UPTODATE = 1, + + __DRBD_A_SET_ROLE_PARMS_MAX, + DRBD_A_SET_ROLE_PARMS_MAX = (__DRBD_A_SET_ROLE_PARMS_MAX - 1) +}; + +enum { + DRBD_A_RESIZE_PARMS_RESIZE_SIZE = 1, + DRBD_A_RESIZE_PARMS_RESIZE_FORCE, + DRBD_A_RESIZE_PARMS_NO_RESYNC, + DRBD_A_RESIZE_PARMS_AL_STRIPES, + DRBD_A_RESIZE_PARMS_AL_STRIPE_SIZE, + + __DRBD_A_RESIZE_PARMS_MAX, + DRBD_A_RESIZE_PARMS_MAX = (__DRBD_A_RESIZE_PARMS_MAX - 1) +}; + +enum { + DRBD_A_STATE_INFO_SIB_REASON = 1, + DRBD_A_STATE_INFO_CURRENT_STATE, + DRBD_A_STATE_INFO_CAPACITY, + DRBD_A_STATE_INFO_ED_UUID, + DRBD_A_STATE_INFO_PREV_STATE, + DRBD_A_STATE_INFO_NEW_STATE, + DRBD_A_STATE_INFO_UUIDS, + DRBD_A_STATE_INFO_DISK_FLAGS, + DRBD_A_STATE_INFO_BITS_TOTAL, + DRBD_A_STATE_INFO_BITS_OOS, + DRBD_A_STATE_INFO_BITS_RS_TOTAL, + DRBD_A_STATE_INFO_BITS_RS_FAILED, + DRBD_A_STATE_INFO_HELPER, + DRBD_A_STATE_INFO_HELPER_EXIT_CODE, + DRBD_A_STATE_INFO_SEND_CNT, + DRBD_A_STATE_INFO_RECV_CNT, + DRBD_A_STATE_INFO_READ_CNT, + DRBD_A_STATE_INFO_WRIT_CNT, + DRBD_A_STATE_INFO_AL_WRIT_CNT, + DRBD_A_STATE_INFO_BM_WRIT_CNT, + DRBD_A_STATE_INFO_AP_BIO_CNT, + DRBD_A_STATE_INFO_AP_PENDING_CNT, + DRBD_A_STATE_INFO_RS_PENDING_CNT, + + __DRBD_A_STATE_INFO_MAX, + DRBD_A_STATE_INFO_MAX = (__DRBD_A_STATE_INFO_MAX - 1) +}; + +enum { + DRBD_A_START_OV_PARMS_OV_START_SECTOR = 1, + DRBD_A_START_OV_PARMS_OV_STOP_SECTOR, + + __DRBD_A_START_OV_PARMS_MAX, + DRBD_A_START_OV_PARMS_MAX = (__DRBD_A_START_OV_PARMS_MAX - 1) +}; + +enum { + DRBD_A_NEW_C_UUID_PARMS_CLEAR_BM = 1, + + __DRBD_A_NEW_C_UUID_PARMS_MAX, + DRBD_A_NEW_C_UUID_PARMS_MAX = (__DRBD_A_NEW_C_UUID_PARMS_MAX - 1) +}; + +enum { + DRBD_A_TIMEOUT_PARMS_TIMEOUT_TYPE = 1, + + __DRBD_A_TIMEOUT_PARMS_MAX, + DRBD_A_TIMEOUT_PARMS_MAX = (__DRBD_A_TIMEOUT_PARMS_MAX - 1) +}; + +enum { + DRBD_A_DISCONNECT_PARMS_FORCE_DISCONNECT = 1, + + __DRBD_A_DISCONNECT_PARMS_MAX, + DRBD_A_DISCONNECT_PARMS_MAX = (__DRBD_A_DISCONNECT_PARMS_MAX - 1) +}; + +enum { + DRBD_A_DETACH_PARMS_FORCE_DETACH = 1, + + __DRBD_A_DETACH_PARMS_MAX, + DRBD_A_DETACH_PARMS_MAX = (__DRBD_A_DETACH_PARMS_MAX - 1) +}; + +enum { + DRBD_A_RESOURCE_INFO_RES_ROLE = 1, + DRBD_A_RESOURCE_INFO_RES_SUSP, + DRBD_A_RESOURCE_INFO_RES_SUSP_NOD, + DRBD_A_RESOURCE_INFO_RES_SUSP_FEN, + + __DRBD_A_RESOURCE_INFO_MAX, + DRBD_A_RESOURCE_INFO_MAX = (__DRBD_A_RESOURCE_INFO_MAX - 1) +}; + +enum { + DRBD_A_DEVICE_INFO_DEV_DISK_STATE = 1, + + __DRBD_A_DEVICE_INFO_MAX, + DRBD_A_DEVICE_INFO_MAX = (__DRBD_A_DEVICE_INFO_MAX - 1) +}; + +enum { + DRBD_A_CONNECTION_INFO_CONN_CONNECTION_STATE = 1, + DRBD_A_CONNECTION_INFO_CONN_ROLE, + + __DRBD_A_CONNECTION_INFO_MAX, + DRBD_A_CONNECTION_INFO_MAX = (__DRBD_A_CONNECTION_INFO_MAX - 1) +}; + +enum { + DRBD_A_PEER_DEVICE_INFO_PEER_REPL_STATE = 1, + DRBD_A_PEER_DEVICE_INFO_PEER_DISK_STATE, + DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_USER, + DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_PEER, + DRBD_A_PEER_DEVICE_INFO_PEER_RESYNC_SUSP_DEPENDENCY, + + __DRBD_A_PEER_DEVICE_INFO_MAX, + DRBD_A_PEER_DEVICE_INFO_MAX = (__DRBD_A_PEER_DEVICE_INFO_MAX - 1) +}; + +enum { + DRBD_A_RESOURCE_STATISTICS_RES_STAT_WRITE_ORDERING = 1, + + __DRBD_A_RESOURCE_STATISTICS_MAX, + DRBD_A_RESOURCE_STATISTICS_MAX = (__DRBD_A_RESOURCE_STATISTICS_MAX - 1) +}; + +enum { + DRBD_A_DEVICE_STATISTICS_DEV_SIZE = 1, + DRBD_A_DEVICE_STATISTICS_DEV_READ, + DRBD_A_DEVICE_STATISTICS_DEV_WRITE, + DRBD_A_DEVICE_STATISTICS_DEV_AL_WRITES, + DRBD_A_DEVICE_STATISTICS_DEV_BM_WRITES, + DRBD_A_DEVICE_STATISTICS_DEV_UPPER_PENDING, + DRBD_A_DEVICE_STATISTICS_DEV_LOWER_PENDING, + DRBD_A_DEVICE_STATISTICS_DEV_UPPER_BLOCKED, + DRBD_A_DEVICE_STATISTICS_DEV_LOWER_BLOCKED, + DRBD_A_DEVICE_STATISTICS_DEV_AL_SUSPENDED, + DRBD_A_DEVICE_STATISTICS_DEV_EXPOSED_DATA_UUID, + DRBD_A_DEVICE_STATISTICS_DEV_CURRENT_UUID, + DRBD_A_DEVICE_STATISTICS_DEV_DISK_FLAGS, + DRBD_A_DEVICE_STATISTICS_HISTORY_UUIDS, + + __DRBD_A_DEVICE_STATISTICS_MAX, + DRBD_A_DEVICE_STATISTICS_MAX = (__DRBD_A_DEVICE_STATISTICS_MAX - 1) +}; + +enum { + DRBD_A_CONNECTION_STATISTICS_CONN_CONGESTED = 1, + + __DRBD_A_CONNECTION_STATISTICS_MAX, + DRBD_A_CONNECTION_STATISTICS_MAX = (__DRBD_A_CONNECTION_STATISTICS_MAX - 1) +}; + +enum { + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_RECEIVED = 1, + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_SENT, + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_PENDING, + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_UNACKED, + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_OUT_OF_SYNC, + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_RESYNC_FAILED, + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_BITMAP_UUID, + DRBD_A_PEER_DEVICE_STATISTICS_PEER_DEV_FLAGS = 9, + + __DRBD_A_PEER_DEVICE_STATISTICS_MAX, + DRBD_A_PEER_DEVICE_STATISTICS_MAX = (__DRBD_A_PEER_DEVICE_STATISTICS_MAX - 1) +}; + +enum { + DRBD_A_DRBD_NOTIFICATION_HEADER_NH_TYPE = 1, + + __DRBD_A_DRBD_NOTIFICATION_HEADER_MAX, + DRBD_A_DRBD_NOTIFICATION_HEADER_MAX = (__DRBD_A_DRBD_NOTIFICATION_HEADER_MAX - 1) +}; + +enum { + DRBD_A_DRBD_HELPER_INFO_HELPER_NAME = 1, + DRBD_A_DRBD_HELPER_INFO_HELPER_STATUS, + + __DRBD_A_DRBD_HELPER_INFO_MAX, + DRBD_A_DRBD_HELPER_INFO_MAX = (__DRBD_A_DRBD_HELPER_INFO_MAX - 1) +}; + +enum { + DRBD_ADM_EVENT = 1, + DRBD_ADM_GET_STATUS, + DRBD_ADM_NEW_MINOR = 5, + DRBD_ADM_DEL_MINOR, + DRBD_ADM_NEW_RESOURCE, + DRBD_ADM_DEL_RESOURCE, + DRBD_ADM_RESOURCE_OPTS, + DRBD_ADM_CONNECT, + DRBD_ADM_DISCONNECT, + DRBD_ADM_ATTACH, + DRBD_ADM_RESIZE, + DRBD_ADM_PRIMARY, + DRBD_ADM_SECONDARY, + DRBD_ADM_NEW_C_UUID, + DRBD_ADM_START_OV, + DRBD_ADM_DETACH, + DRBD_ADM_INVALIDATE, + DRBD_ADM_INVAL_PEER, + DRBD_ADM_PAUSE_SYNC, + DRBD_ADM_RESUME_SYNC, + DRBD_ADM_SUSPEND_IO, + DRBD_ADM_RESUME_IO, + DRBD_ADM_OUTDATE, + DRBD_ADM_GET_TIMEOUT_TYPE, + DRBD_ADM_DOWN, + DRBD_ADM_CHG_DISK_OPTS, + DRBD_ADM_CHG_NET_OPTS, + DRBD_ADM_GET_RESOURCES, + DRBD_ADM_GET_DEVICES, + DRBD_ADM_GET_CONNECTIONS, + DRBD_ADM_GET_PEER_DEVICES, + DRBD_ADM_RESOURCE_STATE, + DRBD_ADM_DEVICE_STATE, + DRBD_ADM_CONNECTION_STATE, + DRBD_ADM_PEER_DEVICE_STATE, + DRBD_ADM_GET_INITIAL_STATE, + DRBD_ADM_HELPER = 40, + DRBD_ADM_INITIAL_STATE_DONE, + + __DRBD_ADM_MAX, + DRBD_ADM_MAX = (__DRBD_ADM_MAX - 1) +}; + +#define DRBD_MCGRP_EVENTS "events" + +#endif /* _UAPI_LINUX_DRBD_GENL_H */ -- cgit v1.3-14-g43fede From 3035e4454142327ec5faee2ff57ab7cb1e9fc712 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 7 May 2026 04:52:55 -0400 Subject: fs: Add case sensitivity flags to file_kattr Enable upper layers such as NFSD to retrieve case sensitivity information from file systems by adding FS_XFLAG_CASEFOLD and FS_XFLAG_CASENONPRESERVING flags. Filesystems report case-insensitive or case-nonpreserving behavior by setting these flags directly in fa->fsx_xflags. The default (flags unset) indicates POSIX semantics: case-sensitive and case-preserving. Both flags are added to FS_XFLAG_RDONLY_MASK so FS_IOC_FSSETXATTR silently strips them, keeping the new xflags strictly a reporting interface. Callers that want to toggle casefolding continue to use FS_IOC_SETFLAGS with FS_CASEFOLD_FL, the established UAPI on filesystems that support the operation (ext4 and f2fs on empty directories). Case sensitivity information is exported to userspace via the fa_xflags field in the FS_IOC_FSGETXATTR ioctl and file_getattr() system call. Reviewed-by: "Darrick J. Wong" Reviewed-by: Jan Kara Reviewed-by: Roland Mainz Signed-off-by: Chuck Lever Link: https://patch.msgid.link/20260507-case-sensitivity-v14-2-e62cc8200435@oracle.com Signed-off-by: Christian Brauner --- fs/file_attr.c | 4 ++++ include/linux/fileattr.h | 3 ++- include/uapi/linux/fs.h | 7 +++++++ 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/file_attr.c b/fs/file_attr.c index f429da66a317..bfb00d256dd5 100644 --- a/fs/file_attr.c +++ b/fs/file_attr.c @@ -37,6 +37,8 @@ void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags) fa->flags |= FS_PROJINHERIT_FL; if (fa->fsx_xflags & FS_XFLAG_VERITY) fa->flags |= FS_VERITY_FL; + if (fa->fsx_xflags & FS_XFLAG_CASEFOLD) + fa->flags |= FS_CASEFOLD_FL; } EXPORT_SYMBOL(fileattr_fill_xflags); @@ -67,6 +69,8 @@ void fileattr_fill_flags(struct file_kattr *fa, u32 flags) fa->fsx_xflags |= FS_XFLAG_PROJINHERIT; if (fa->flags & FS_VERITY_FL) fa->fsx_xflags |= FS_XFLAG_VERITY; + if (fa->flags & FS_CASEFOLD_FL) + fa->fsx_xflags |= FS_XFLAG_CASEFOLD; } EXPORT_SYMBOL(fileattr_fill_flags); diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h index 3780904a63a6..58044b598016 100644 --- a/include/linux/fileattr.h +++ b/include/linux/fileattr.h @@ -16,7 +16,8 @@ /* Read-only inode flags */ #define FS_XFLAG_RDONLY_MASK \ - (FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR | FS_XFLAG_VERITY) + (FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR | FS_XFLAG_VERITY | \ + FS_XFLAG_CASEFOLD | FS_XFLAG_CASENONPRESERVING) /* Flags to indicate valid value of fsx_ fields */ #define FS_XFLAG_VALUES_MASK \ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 13f71202845e..2ea4c81df08f 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -254,6 +254,13 @@ struct file_attr { #define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */ #define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ #define FS_XFLAG_VERITY 0x00020000 /* fs-verity enabled */ +/* + * Case handling flags (read-only, cannot be set via ioctl). + * Default (neither set) indicates POSIX semantics: case-sensitive + * lookups and case-preserving storage. + */ +#define FS_XFLAG_CASEFOLD 0x00040000 /* case-insensitive lookups */ +#define FS_XFLAG_CASENONPRESERVING 0x00080000 /* case not preserved */ #define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ /* the read-only stuff doesn't really belong here, but any other place is -- cgit v1.3-14-g43fede From 61848e9799f2543a3ea144e277b17aaec9707566 Mon Sep 17 00:00:00 2001 From: Ethan Nelson-Moore Date: Sun, 3 May 2026 20:14:53 -0700 Subject: tty: synclink_gt: remove broken driver The synclink_gt driver was marked as broken in commit 426263d5fb40 ("tty: synclink_gt: mark as BROKEN") in July 2023 because it had severe structural problems and there had been no evidence of users since 2016. Since then, no meaningful improvements have been made to the driver, and it is unlikely that will ever happen due to the lack of interest. Drop the driver and references to it in comments and documentation. include/uapi/linux/synclink.h is also removed. The only use of this header I have found is the linux-raw-sys Rust crate. It generates bindings for all UAPI headers, but has a hardcoded list of headers and ioctls, including this one, so that does not indicate that anyone is using it. I have sent a pull request to remove the include and ioctl definitions for this header (see the link below). Link: https://github.com/sunfishcode/linux-raw-sys/pull/185 Signed-off-by: Ethan Nelson-Moore Acked-by: Jakub Kicinski Link: https://patch.msgid.link/20260504031519.18877-1-enelsonmoore@gmail.com Signed-off-by: Greg Kroah-Hartman --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - drivers/net/ppp/Kconfig | 4 +- drivers/tty/Kconfig | 11 +- drivers/tty/Makefile | 1 - drivers/tty/n_hdlc.c | 7 - drivers/tty/synclink_gt.c | 5038 -------------------- include/linux/synclink.h | 37 - include/uapi/linux/synclink.h | 301 -- 9 files changed, 3 insertions(+), 5398 deletions(-) delete mode 100644 drivers/tty/synclink_gt.c delete mode 100644 include/linux/synclink.h delete mode 100644 include/uapi/linux/synclink.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 331223761fff..58716f4f4834 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -271,7 +271,6 @@ Code Seq# Include File Comments 'm' 00-09 linux/mmtimer.h conflict! 'm' all linux/mtio.h conflict! 'm' all linux/soundcard.h conflict! -'m' all linux/synclink.h conflict! 'm' 00-19 drivers/message/fusion/mptctl.h conflict! 'm' 00 drivers/scsi/megaraid/megaraid_ioctl.h conflict! 'n' 00-7F linux/ncp_fs.h and fs/ncpfs/ioctl.c diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index ccabc6e17168..4ddd2c01b8b7 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -551,7 +551,6 @@ CONFIG_GAMEPORT_EMU10K1=m CONFIG_GAMEPORT_FM801=m # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_NONSTANDARD=y -CONFIG_SYNCLINK_GT=m CONFIG_NOZOMI=m CONFIG_N_HDLC=m CONFIG_SERIAL_8250=y diff --git a/drivers/net/ppp/Kconfig b/drivers/net/ppp/Kconfig index 753354b4e36c..5324e2102383 100644 --- a/drivers/net/ppp/Kconfig +++ b/drivers/net/ppp/Kconfig @@ -191,8 +191,8 @@ config PPP_SYNC_TTY tristate "PPP support for sync tty ports" help Say Y (or M) here if you want to be able to use PPP over synchronous - (HDLC) tty devices, such as the SyncLink adapter. These devices - are often used for high-speed leased lines like T1/E1. + (HDLC) tty devices. These devices are often used for high-speed leased + lines like T1/E1. To compile this driver as a module, choose M here. diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig index 149f3d53b760..df6832a4c237 100644 --- a/drivers/tty/Kconfig +++ b/drivers/tty/Kconfig @@ -231,21 +231,12 @@ config MOXA_SMARTIO This driver can also be built as a module. The module will be called mxser. If you want to do that, say M here. -config SYNCLINK_GT - tristate "SyncLink GT/AC support" - depends on SERIAL_NONSTANDARD && PCI - depends on BROKEN - help - Support for SyncLink GT and SyncLink AC families of - synchronous and asynchronous serial adapters - manufactured by Microgate Systems, Ltd. (www.microgate.com) - config N_HDLC tristate "HDLC line discipline support" depends on SERIAL_NONSTANDARD help Allows synchronous HDLC communications with tty device drivers that - support synchronous HDLC such as the Microgate SyncLink adapter. + support synchronous HDLC. This driver can be built as a module ( = code which can be inserted in and removed from the running kernel whenever you want). diff --git a/drivers/tty/Makefile b/drivers/tty/Makefile index 07aca5184a55..8ca1a0a2229f 100644 --- a/drivers/tty/Makefile +++ b/drivers/tty/Makefile @@ -21,7 +21,6 @@ obj-$(CONFIG_MOXA_INTELLIO) += moxa.o obj-$(CONFIG_MOXA_SMARTIO) += mxser.o obj-$(CONFIG_NOZOMI) += nozomi.o obj-$(CONFIG_NULL_TTY) += ttynull.o -obj-$(CONFIG_SYNCLINK_GT) += synclink_gt.o obj-$(CONFIG_PPC_EPAPR_HV_BYTECHAN) += ehv_bytechan.o obj-$(CONFIG_GOLDFISH_TTY) += goldfish.o obj-$(CONFIG_MIPS_EJTAG_FDC_TTY) += mips_ejtag_fdc.o diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 98eefa2cede4..895b850a5950 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -4,8 +4,6 @@ * Written by Paul Fulghum paulkf@microgate.com * for Microgate Corporation * - * Microgate and SyncLink are registered trademarks of Microgate Corporation - * * Adapted from ppp.c, written by Michael Callahan , * Al Longyear , * Paul Mackerras @@ -54,11 +52,6 @@ * this line discipline (or another line discipline that is frame * oriented such as N_PPP). * - * The SyncLink driver (synclink.c) implements both asynchronous - * (using standard line discipline N_TTY) and synchronous HDLC - * (using N_HDLC) communications, with the latter using the above - * conventions. - * * This implementation is very basic and does not maintain * any statistics. The main point is to enforce the raw data * and frame orientation of HDLC communications. diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c deleted file mode 100644 index bf4f50e0ce94..000000000000 --- a/drivers/tty/synclink_gt.c +++ /dev/null @@ -1,5038 +0,0 @@ -// SPDX-License-Identifier: GPL-1.0+ -/* - * Device driver for Microgate SyncLink GT serial adapters. - * - * written by Paul Fulghum for Microgate Corporation - * paulkf@microgate.com - * - * Microgate and SyncLink are trademarks of Microgate Corporation - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES - * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, - * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR - * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, - * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -/* - * DEBUG OUTPUT DEFINITIONS - * - * uncomment lines below to enable specific types of debug output - * - * DBGINFO information - most verbose output - * DBGERR serious errors - * DBGBH bottom half service routine debugging - * DBGISR interrupt service routine debugging - * DBGDATA output receive and transmit data - * DBGTBUF output transmit DMA buffers and registers - * DBGRBUF output receive DMA buffers and registers - */ - -#define DBGINFO(fmt) if (debug_level >= DEBUG_LEVEL_INFO) printk fmt -#define DBGERR(fmt) if (debug_level >= DEBUG_LEVEL_ERROR) printk fmt -#define DBGBH(fmt) if (debug_level >= DEBUG_LEVEL_BH) printk fmt -#define DBGISR(fmt) if (debug_level >= DEBUG_LEVEL_ISR) printk fmt -#define DBGDATA(info, buf, size, label) if (debug_level >= DEBUG_LEVEL_DATA) trace_block((info), (buf), (size), (label)) -/*#define DBGTBUF(info) dump_tbufs(info)*/ -/*#define DBGRBUF(info) dump_rbufs(info)*/ - - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -#if defined(CONFIG_HDLC) || (defined(CONFIG_HDLC_MODULE) && defined(CONFIG_SYNCLINK_GT_MODULE)) -#define SYNCLINK_GENERIC_HDLC 1 -#else -#define SYNCLINK_GENERIC_HDLC 0 -#endif - -/* - * module identification - */ -static const char driver_name[] = "SyncLink GT"; -static const char tty_dev_prefix[] = "ttySLG"; -MODULE_DESCRIPTION("Device driver for Microgate SyncLink GT serial adapters"); -MODULE_LICENSE("GPL"); -#define MAX_DEVICES 32 - -static const struct pci_device_id pci_table[] = { - { PCI_VDEVICE(MICROGATE, SYNCLINK_GT_DEVICE_ID) }, - { PCI_VDEVICE(MICROGATE, SYNCLINK_GT2_DEVICE_ID) }, - { PCI_VDEVICE(MICROGATE, SYNCLINK_GT4_DEVICE_ID) }, - { PCI_VDEVICE(MICROGATE, SYNCLINK_AC_DEVICE_ID) }, - { 0 }, /* terminate list */ -}; -MODULE_DEVICE_TABLE(pci, pci_table); - -static int init_one(struct pci_dev *dev,const struct pci_device_id *ent); -static void remove_one(struct pci_dev *dev); -static struct pci_driver pci_driver = { - .name = "synclink_gt", - .id_table = pci_table, - .probe = init_one, - .remove = remove_one, -}; - -static bool pci_registered; - -/* - * module configuration and status - */ -static struct slgt_info *slgt_device_list; -static int slgt_device_count; - -static int ttymajor; -static int debug_level; -static int maxframe[MAX_DEVICES]; - -module_param(ttymajor, int, 0); -module_param(debug_level, int, 0); -module_param_array(maxframe, int, NULL, 0); - -MODULE_PARM_DESC(ttymajor, "TTY major device number override: 0=auto assigned"); -MODULE_PARM_DESC(debug_level, "Debug syslog output: 0=disabled, 1 to 5=increasing detail"); -MODULE_PARM_DESC(maxframe, "Maximum frame size used by device (4096 to 65535)"); - -/* - * tty support and callbacks - */ -static struct tty_driver *serial_driver; - -static void wait_until_sent(struct tty_struct *tty, int timeout); -static void flush_buffer(struct tty_struct *tty); -static void tx_release(struct tty_struct *tty); - -/* - * generic HDLC support - */ -#define dev_to_port(D) (dev_to_hdlc(D)->priv) - - -/* - * device specific structures, macros and functions - */ - -#define SLGT_MAX_PORTS 4 -#define SLGT_REG_SIZE 256 - -/* - * conditional wait facility - */ -struct cond_wait { - struct cond_wait *next; - wait_queue_head_t q; - wait_queue_entry_t wait; - unsigned int data; -}; -static void flush_cond_wait(struct cond_wait **head); - -/* - * DMA buffer descriptor and access macros - */ -struct slgt_desc -{ - __le16 count; - __le16 status; - __le32 pbuf; /* physical address of data buffer */ - __le32 next; /* physical address of next descriptor */ - - /* driver book keeping */ - char *buf; /* virtual address of data buffer */ - unsigned int pdesc; /* physical address of this descriptor */ - dma_addr_t buf_dma_addr; - unsigned short buf_count; -}; - -#define set_desc_buffer(a,b) (a).pbuf = cpu_to_le32((unsigned int)(b)) -#define set_desc_next(a,b) (a).next = cpu_to_le32((unsigned int)(b)) -#define set_desc_count(a,b)(a).count = cpu_to_le16((unsigned short)(b)) -#define set_desc_eof(a,b) (a).status = cpu_to_le16((b) ? (le16_to_cpu((a).status) | BIT0) : (le16_to_cpu((a).status) & ~BIT0)) -#define set_desc_status(a, b) (a).status = cpu_to_le16((unsigned short)(b)) -#define desc_count(a) (le16_to_cpu((a).count)) -#define desc_status(a) (le16_to_cpu((a).status)) -#define desc_complete(a) (le16_to_cpu((a).status) & BIT15) -#define desc_eof(a) (le16_to_cpu((a).status) & BIT2) -#define desc_crc_error(a) (le16_to_cpu((a).status) & BIT1) -#define desc_abort(a) (le16_to_cpu((a).status) & BIT0) -#define desc_residue(a) ((le16_to_cpu((a).status) & 0x38) >> 3) - -struct _input_signal_events { - int ri_up; - int ri_down; - int dsr_up; - int dsr_down; - int dcd_up; - int dcd_down; - int cts_up; - int cts_down; -}; - -/* - * device instance data structure - */ -struct slgt_info { - void *if_ptr; /* General purpose pointer (used by SPPP) */ - struct tty_port port; - - struct slgt_info *next_device; /* device list link */ - - char device_name[25]; - struct pci_dev *pdev; - - int port_count; /* count of ports on adapter */ - int adapter_num; /* adapter instance number */ - int port_num; /* port instance number */ - - /* array of pointers to port contexts on this adapter */ - struct slgt_info *port_array[SLGT_MAX_PORTS]; - - int line; /* tty line instance number */ - - struct mgsl_icount icount; - - int timeout; - int x_char; /* xon/xoff character */ - unsigned int read_status_mask; - unsigned int ignore_status_mask; - - wait_queue_head_t status_event_wait_q; - wait_queue_head_t event_wait_q; - struct timer_list tx_timer; - struct timer_list rx_timer; - - unsigned int gpio_present; - struct cond_wait *gpio_wait_q; - - spinlock_t lock; /* spinlock for synchronizing with ISR */ - - struct work_struct task; - u32 pending_bh; - bool bh_requested; - bool bh_running; - - int isr_overflow; - bool irq_requested; /* true if IRQ requested */ - bool irq_occurred; /* for diagnostics use */ - - /* device configuration */ - - unsigned int bus_type; - unsigned int irq_level; - unsigned long irq_flags; - - unsigned char __iomem * reg_addr; /* memory mapped registers address */ - u32 phys_reg_addr; - bool reg_addr_requested; - - MGSL_PARAMS params; /* communications parameters */ - u32 idle_mode; - u32 max_frame_size; /* as set by device config */ - - unsigned int rbuf_fill_level; - unsigned int rx_pio; - unsigned int if_mode; - unsigned int base_clock; - unsigned int xsync; - unsigned int xctrl; - - /* device status */ - - bool rx_enabled; - bool rx_restart; - - bool tx_enabled; - bool tx_active; - - unsigned char signals; /* serial signal states */ - int init_error; /* initialization error */ - - unsigned char *tx_buf; - int tx_count; - - bool drop_rts_on_tx_done; - struct _input_signal_events input_signal_events; - - int dcd_chkcount; /* check counts to prevent */ - int cts_chkcount; /* too many IRQs if a signal */ - int dsr_chkcount; /* is floating */ - int ri_chkcount; - - char *bufs; /* virtual address of DMA buffer lists */ - dma_addr_t bufs_dma_addr; /* physical address of buffer descriptors */ - - unsigned int rbuf_count; - struct slgt_desc *rbufs; - unsigned int rbuf_current; - unsigned int rbuf_index; - unsigned int rbuf_fill_index; - unsigned short rbuf_fill_count; - - unsigned int tbuf_count; - struct slgt_desc *tbufs; - unsigned int tbuf_current; - unsigned int tbuf_start; - - unsigned char *tmp_rbuf; - unsigned int tmp_rbuf_count; - - /* SPPP/Cisco HDLC device parts */ - - int netcount; - spinlock_t netlock; -#if SYNCLINK_GENERIC_HDLC - struct net_device *netdev; -#endif - -}; - -static const MGSL_PARAMS default_params = { - .mode = MGSL_MODE_HDLC, - .loopback = 0, - .flags = HDLC_FLAG_UNDERRUN_ABORT15, - .encoding = HDLC_ENCODING_NRZI_SPACE, - .clock_speed = 0, - .addr_filter = 0xff, - .crc_type = HDLC_CRC_16_CCITT, - .preamble_length = HDLC_PREAMBLE_LENGTH_8BITS, - .preamble = HDLC_PREAMBLE_PATTERN_NONE, - .data_rate = 9600, - .data_bits = 8, - .stop_bits = 1, - .parity = ASYNC_PARITY_NONE -}; - - -#define BH_RECEIVE 1 -#define BH_TRANSMIT 2 -#define BH_STATUS 4 -#define IO_PIN_SHUTDOWN_LIMIT 100 - -#define DMABUFSIZE 256 -#define DESC_LIST_SIZE 4096 - -#define MASK_PARITY BIT1 -#define MASK_FRAMING BIT0 -#define MASK_BREAK BIT14 -#define MASK_OVERRUN BIT4 - -#define GSR 0x00 /* global status */ -#define JCR 0x04 /* JTAG control */ -#define IODR 0x08 /* GPIO direction */ -#define IOER 0x0c /* GPIO interrupt enable */ -#define IOVR 0x10 /* GPIO value */ -#define IOSR 0x14 /* GPIO interrupt status */ -#define TDR 0x80 /* tx data */ -#define RDR 0x80 /* rx data */ -#define TCR 0x82 /* tx control */ -#define TIR 0x84 /* tx idle */ -#define TPR 0x85 /* tx preamble */ -#define RCR 0x86 /* rx control */ -#define VCR 0x88 /* V.24 control */ -#define CCR 0x89 /* clock control */ -#define BDR 0x8a /* baud divisor */ -#define SCR 0x8c /* serial control */ -#define SSR 0x8e /* serial status */ -#define RDCSR 0x90 /* rx DMA control/status */ -#define TDCSR 0x94 /* tx DMA control/status */ -#define RDDAR 0x98 /* rx DMA descriptor address */ -#define TDDAR 0x9c /* tx DMA descriptor address */ -#define XSR 0x40 /* extended sync pattern */ -#define XCR 0x44 /* extended control */ - -#define RXIDLE BIT14 -#define RXBREAK BIT14 -#define IRQ_TXDATA BIT13 -#define IRQ_TXIDLE BIT12 -#define IRQ_TXUNDER BIT11 /* HDLC */ -#define IRQ_RXDATA BIT10 -#define IRQ_RXIDLE BIT9 /* HDLC */ -#define IRQ_RXBREAK BIT9 /* async */ -#define IRQ_RXOVER BIT8 -#define IRQ_DSR BIT7 -#define IRQ_CTS BIT6 -#define IRQ_DCD BIT5 -#define IRQ_RI BIT4 -#define IRQ_ALL 0x3ff0 -#define IRQ_MASTER BIT0 - -#define slgt_irq_on(info, mask) \ - wr_reg16((info), SCR, (unsigned short)(rd_reg16((info), SCR) | (mask))) -#define slgt_irq_off(info, mask) \ - wr_reg16((info), SCR, (unsigned short)(rd_reg16((info), SCR) & ~(mask))) - -static __u8 rd_reg8(struct slgt_info *info, unsigned int addr); -static void wr_reg8(struct slgt_info *info, unsigned int addr, __u8 value); -static __u16 rd_reg16(struct slgt_info *info, unsigned int addr); -static void wr_reg16(struct slgt_info *info, unsigned int addr, __u16 value); -static __u32 rd_reg32(struct slgt_info *info, unsigned int addr); -static void wr_reg32(struct slgt_info *info, unsigned int addr, __u32 value); - -static void msc_set_vcr(struct slgt_info *info); - -static int startup_hw(struct slgt_info *info); -static int block_til_ready(struct tty_struct *tty, struct file * filp,struct slgt_info *info); -static void shutdown_hw(struct slgt_info *info); -static void program_hw(struct slgt_info *info); -static void change_params(struct slgt_info *info); - -static int adapter_test(struct slgt_info *info); - -static void reset_port(struct slgt_info *info); -static void async_mode(struct slgt_info *info); -static void sync_mode(struct slgt_info *info); - -static void rx_stop(struct slgt_info *info); -static void rx_start(struct slgt_info *info); -static void reset_rbufs(struct slgt_info *info); -static void free_rbufs(struct slgt_info *info, unsigned int first, unsigned int last); -static bool rx_get_frame(struct slgt_info *info); -static bool rx_get_buf(struct slgt_info *info); - -static void tx_start(struct slgt_info *info); -static void tx_stop(struct slgt_info *info); -static void tx_set_idle(struct slgt_info *info); -static unsigned int tbuf_bytes(struct slgt_info *info); -static void reset_tbufs(struct slgt_info *info); -static void tdma_reset(struct slgt_info *info); -static bool tx_load(struct slgt_info *info, const u8 *buf, unsigned int count); - -static void get_gtsignals(struct slgt_info *info); -static void set_gtsignals(struct slgt_info *info); -static void set_rate(struct slgt_info *info, u32 data_rate); - -static void bh_transmit(struct slgt_info *info); -static void isr_txeom(struct slgt_info *info, unsigned short status); - -static void tx_timeout(struct timer_list *t); -static void rx_timeout(struct timer_list *t); - -/* - * ioctl handlers - */ -static int get_stats(struct slgt_info *info, struct mgsl_icount __user *user_icount); -static int get_params(struct slgt_info *info, MGSL_PARAMS __user *params); -static int set_params(struct slgt_info *info, MGSL_PARAMS __user *params); -static int get_txidle(struct slgt_info *info, int __user *idle_mode); -static int set_txidle(struct slgt_info *info, int idle_mode); -static int tx_enable(struct slgt_info *info, int enable); -static int tx_abort(struct slgt_info *info); -static int rx_enable(struct slgt_info *info, int enable); -static int modem_input_wait(struct slgt_info *info,int arg); -static int wait_mgsl_event(struct slgt_info *info, int __user *mask_ptr); -static int get_interface(struct slgt_info *info, int __user *if_mode); -static int set_interface(struct slgt_info *info, int if_mode); -static int set_gpio(struct slgt_info *info, struct gpio_desc __user *gpio); -static int get_gpio(struct slgt_info *info, struct gpio_desc __user *gpio); -static int wait_gpio(struct slgt_info *info, struct gpio_desc __user *gpio); -static int get_xsync(struct slgt_info *info, int __user *if_mode); -static int set_xsync(struct slgt_info *info, int if_mode); -static int get_xctrl(struct slgt_info *info, int __user *if_mode); -static int set_xctrl(struct slgt_info *info, int if_mode); - -/* - * driver functions - */ -static void release_resources(struct slgt_info *info); - -/* - * DEBUG OUTPUT CODE - */ -#ifndef DBGINFO -#define DBGINFO(fmt) -#endif -#ifndef DBGERR -#define DBGERR(fmt) -#endif -#ifndef DBGBH -#define DBGBH(fmt) -#endif -#ifndef DBGISR -#define DBGISR(fmt) -#endif - -#ifdef DBGDATA -static void trace_block(struct slgt_info *info, const char *data, int count, const char *label) -{ - int i; - int linecount; - printk("%s %s data:\n",info->device_name, label); - while(count) { - linecount = (count > 16) ? 16 : count; - for(i=0; i < linecount; i++) - printk("%02X ",(unsigned char)data[i]); - for(;i<17;i++) - printk(" "); - for(i=0;i=040 && data[i]<=0176) - printk("%c",data[i]); - else - printk("."); - } - printk("\n"); - data += linecount; - count -= linecount; - } -} -#else -#define DBGDATA(info, buf, size, label) -#endif - -#ifdef DBGTBUF -static void dump_tbufs(struct slgt_info *info) -{ - int i; - printk("tbuf_current=%d\n", info->tbuf_current); - for (i=0 ; i < info->tbuf_count ; i++) { - printk("%d: count=%04X status=%04X\n", - i, le16_to_cpu(info->tbufs[i].count), le16_to_cpu(info->tbufs[i].status)); - } -} -#else -#define DBGTBUF(info) -#endif - -#ifdef DBGRBUF -static void dump_rbufs(struct slgt_info *info) -{ - int i; - printk("rbuf_current=%d\n", info->rbuf_current); - for (i=0 ; i < info->rbuf_count ; i++) { - printk("%d: count=%04X status=%04X\n", - i, le16_to_cpu(info->rbufs[i].count), le16_to_cpu(info->rbufs[i].status)); - } -} -#else -#define DBGRBUF(info) -#endif - -static inline int sanity_check(struct slgt_info *info, char *devname, const char *name) -{ -#ifdef SANITY_CHECK - if (!info) { - printk("null struct slgt_info for (%s) in %s\n", devname, name); - return 1; - } -#else - if (!info) - return 1; -#endif - return 0; -} - -/* - * line discipline callback wrappers - * - * The wrappers maintain line discipline references - * while calling into the line discipline. - * - * ldisc_receive_buf - pass receive data to line discipline - */ -static void ldisc_receive_buf(struct tty_struct *tty, - const __u8 *data, char *flags, int count) -{ - struct tty_ldisc *ld; - if (!tty) - return; - ld = tty_ldisc_ref(tty); - if (ld) { - if (ld->ops->receive_buf) - ld->ops->receive_buf(tty, data, flags, count); - tty_ldisc_deref(ld); - } -} - -/* tty callbacks */ - -static int open(struct tty_struct *tty, struct file *filp) -{ - struct slgt_info *info; - int retval, line; - unsigned long flags; - - line = tty->index; - if (line >= slgt_device_count) { - DBGERR(("%s: open with invalid line #%d.\n", driver_name, line)); - return -ENODEV; - } - - info = slgt_device_list; - while(info && info->line != line) - info = info->next_device; - if (sanity_check(info, tty->name, "open")) - return -ENODEV; - if (info->init_error) { - DBGERR(("%s init error=%d\n", info->device_name, info->init_error)); - return -ENODEV; - } - - tty->driver_data = info; - info->port.tty = tty; - - DBGINFO(("%s open, old ref count = %d\n", info->device_name, info->port.count)); - - mutex_lock(&info->port.mutex); - - spin_lock_irqsave(&info->netlock, flags); - if (info->netcount) { - retval = -EBUSY; - spin_unlock_irqrestore(&info->netlock, flags); - mutex_unlock(&info->port.mutex); - goto cleanup; - } - info->port.count++; - spin_unlock_irqrestore(&info->netlock, flags); - - if (info->port.count == 1) { - /* 1st open on this device, init hardware */ - retval = startup_hw(info); - if (retval < 0) { - mutex_unlock(&info->port.mutex); - goto cleanup; - } - } - mutex_unlock(&info->port.mutex); - retval = block_til_ready(tty, filp, info); - if (retval) { - DBGINFO(("%s block_til_ready rc=%d\n", info->device_name, retval)); - goto cleanup; - } - - retval = 0; - -cleanup: - if (retval) { - if (tty->count == 1) - info->port.tty = NULL; /* tty layer will release tty struct */ - if(info->port.count) - info->port.count--; - } - - DBGINFO(("%s open rc=%d\n", info->device_name, retval)); - return retval; -} - -static void close(struct tty_struct *tty, struct file *filp) -{ - struct slgt_info *info = tty->driver_data; - - if (sanity_check(info, tty->name, "close")) - return; - DBGINFO(("%s close entry, count=%d\n", info->device_name, info->port.count)); - - if (tty_port_close_start(&info->port, tty, filp) == 0) - goto cleanup; - - mutex_lock(&info->port.mutex); - if (tty_port_initialized(&info->port)) - wait_until_sent(tty, info->timeout); - flush_buffer(tty); - tty_ldisc_flush(tty); - - shutdown_hw(info); - mutex_unlock(&info->port.mutex); - - tty_port_close_end(&info->port, tty); - info->port.tty = NULL; -cleanup: - DBGINFO(("%s close exit, count=%d\n", tty->driver->name, info->port.count)); -} - -static void hangup(struct tty_struct *tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "hangup")) - return; - DBGINFO(("%s hangup\n", info->device_name)); - - flush_buffer(tty); - - mutex_lock(&info->port.mutex); - shutdown_hw(info); - - spin_lock_irqsave(&info->port.lock, flags); - info->port.count = 0; - info->port.tty = NULL; - spin_unlock_irqrestore(&info->port.lock, flags); - tty_port_set_active(&info->port, false); - mutex_unlock(&info->port.mutex); - - wake_up_interruptible(&info->port.open_wait); -} - -static void set_termios(struct tty_struct *tty, - const struct ktermios *old_termios) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - DBGINFO(("%s set_termios\n", tty->driver->name)); - - change_params(info); - - /* Handle transition to B0 status */ - if ((old_termios->c_cflag & CBAUD) && !C_BAUD(tty)) { - info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - spin_lock_irqsave(&info->lock,flags); - set_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); - } - - /* Handle transition away from B0 status */ - if (!(old_termios->c_cflag & CBAUD) && C_BAUD(tty)) { - info->signals |= SerialSignal_DTR; - if (!C_CRTSCTS(tty) || !tty_throttled(tty)) - info->signals |= SerialSignal_RTS; - spin_lock_irqsave(&info->lock,flags); - set_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); - } - - /* Handle turning off CRTSCTS */ - if ((old_termios->c_cflag & CRTSCTS) && !C_CRTSCTS(tty)) { - tty->hw_stopped = false; - tx_release(tty); - } -} - -static void update_tx_timer(struct slgt_info *info) -{ - /* - * use worst case speed of 1200bps to calculate transmit timeout - * based on data in buffers (tbuf_bytes) and FIFO (128 bytes) - */ - if (info->params.mode == MGSL_MODE_HDLC) { - int timeout = (tbuf_bytes(info) * 7) + 1000; - mod_timer(&info->tx_timer, jiffies + msecs_to_jiffies(timeout)); - } -} - -static ssize_t write(struct tty_struct *tty, const u8 *buf, size_t count) -{ - int ret = 0; - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "write")) - return -EIO; - - DBGINFO(("%s write count=%zu\n", info->device_name, count)); - - if (!info->tx_buf || (count > info->max_frame_size)) - return -EIO; - - if (!count || tty->flow.stopped || tty->hw_stopped) - return 0; - - spin_lock_irqsave(&info->lock, flags); - - if (info->tx_count) { - /* send accumulated data from send_char() */ - if (!tx_load(info, info->tx_buf, info->tx_count)) - goto cleanup; - info->tx_count = 0; - } - - if (tx_load(info, buf, count)) - ret = count; - -cleanup: - spin_unlock_irqrestore(&info->lock, flags); - DBGINFO(("%s write rc=%d\n", info->device_name, ret)); - return ret; -} - -static int put_char(struct tty_struct *tty, u8 ch) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - int ret = 0; - - if (sanity_check(info, tty->name, "put_char")) - return 0; - DBGINFO(("%s put_char(%u)\n", info->device_name, ch)); - if (!info->tx_buf) - return 0; - spin_lock_irqsave(&info->lock,flags); - if (info->tx_count < info->max_frame_size) { - info->tx_buf[info->tx_count++] = ch; - ret = 1; - } - spin_unlock_irqrestore(&info->lock,flags); - return ret; -} - -static void send_xchar(struct tty_struct *tty, char ch) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "send_xchar")) - return; - DBGINFO(("%s send_xchar(%d)\n", info->device_name, ch)); - info->x_char = ch; - if (ch) { - spin_lock_irqsave(&info->lock,flags); - if (!info->tx_enabled) - tx_start(info); - spin_unlock_irqrestore(&info->lock,flags); - } -} - -static void wait_until_sent(struct tty_struct *tty, int timeout) -{ - struct slgt_info *info = tty->driver_data; - unsigned long orig_jiffies, char_time; - - if (!info ) - return; - if (sanity_check(info, tty->name, "wait_until_sent")) - return; - DBGINFO(("%s wait_until_sent entry\n", info->device_name)); - if (!tty_port_initialized(&info->port)) - goto exit; - - orig_jiffies = jiffies; - - /* Set check interval to 1/5 of estimated time to - * send a character, and make it at least 1. The check - * interval should also be less than the timeout. - * Note: use tight timings here to satisfy the NIST-PCTS. - */ - - if (info->params.data_rate) { - char_time = info->timeout/(32 * 5); - if (!char_time) - char_time++; - } else - char_time = 1; - - if (timeout) - char_time = min_t(unsigned long, char_time, timeout); - - while (info->tx_active) { - msleep_interruptible(jiffies_to_msecs(char_time)); - if (signal_pending(current)) - break; - if (timeout && time_after(jiffies, orig_jiffies + timeout)) - break; - } -exit: - DBGINFO(("%s wait_until_sent exit\n", info->device_name)); -} - -static unsigned int write_room(struct tty_struct *tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned int ret; - - if (sanity_check(info, tty->name, "write_room")) - return 0; - ret = (info->tx_active) ? 0 : HDLC_MAX_FRAME_SIZE; - DBGINFO(("%s write_room=%u\n", info->device_name, ret)); - return ret; -} - -static void flush_chars(struct tty_struct *tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "flush_chars")) - return; - DBGINFO(("%s flush_chars entry tx_count=%d\n", info->device_name, info->tx_count)); - - if (info->tx_count <= 0 || tty->flow.stopped || - tty->hw_stopped || !info->tx_buf) - return; - - DBGINFO(("%s flush_chars start transmit\n", info->device_name)); - - spin_lock_irqsave(&info->lock,flags); - if (info->tx_count && tx_load(info, info->tx_buf, info->tx_count)) - info->tx_count = 0; - spin_unlock_irqrestore(&info->lock,flags); -} - -static void flush_buffer(struct tty_struct *tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "flush_buffer")) - return; - DBGINFO(("%s flush_buffer\n", info->device_name)); - - spin_lock_irqsave(&info->lock, flags); - info->tx_count = 0; - spin_unlock_irqrestore(&info->lock, flags); - - tty_wakeup(tty); -} - -/* - * throttle (stop) transmitter - */ -static void tx_hold(struct tty_struct *tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "tx_hold")) - return; - DBGINFO(("%s tx_hold\n", info->device_name)); - spin_lock_irqsave(&info->lock,flags); - if (info->tx_enabled && info->params.mode == MGSL_MODE_ASYNC) - tx_stop(info); - spin_unlock_irqrestore(&info->lock,flags); -} - -/* - * release (start) transmitter - */ -static void tx_release(struct tty_struct *tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "tx_release")) - return; - DBGINFO(("%s tx_release\n", info->device_name)); - spin_lock_irqsave(&info->lock, flags); - if (info->tx_count && tx_load(info, info->tx_buf, info->tx_count)) - info->tx_count = 0; - spin_unlock_irqrestore(&info->lock, flags); -} - -/* - * Service an IOCTL request - * - * Arguments - * - * tty pointer to tty instance data - * cmd IOCTL command code - * arg command argument/context - * - * Return 0 if success, otherwise error code - */ -static int ioctl(struct tty_struct *tty, - unsigned int cmd, unsigned long arg) -{ - struct slgt_info *info = tty->driver_data; - void __user *argp = (void __user *)arg; - int ret; - - if (sanity_check(info, tty->name, "ioctl")) - return -ENODEV; - DBGINFO(("%s ioctl() cmd=%08X\n", info->device_name, cmd)); - - if (cmd != TIOCMIWAIT) { - if (tty_io_error(tty)) - return -EIO; - } - - switch (cmd) { - case MGSL_IOCWAITEVENT: - return wait_mgsl_event(info, argp); - case TIOCMIWAIT: - return modem_input_wait(info,(int)arg); - case MGSL_IOCSGPIO: - return set_gpio(info, argp); - case MGSL_IOCGGPIO: - return get_gpio(info, argp); - case MGSL_IOCWAITGPIO: - return wait_gpio(info, argp); - case MGSL_IOCGXSYNC: - return get_xsync(info, argp); - case MGSL_IOCSXSYNC: - return set_xsync(info, (int)arg); - case MGSL_IOCGXCTRL: - return get_xctrl(info, argp); - case MGSL_IOCSXCTRL: - return set_xctrl(info, (int)arg); - } - mutex_lock(&info->port.mutex); - switch (cmd) { - case MGSL_IOCGPARAMS: - ret = get_params(info, argp); - break; - case MGSL_IOCSPARAMS: - ret = set_params(info, argp); - break; - case MGSL_IOCGTXIDLE: - ret = get_txidle(info, argp); - break; - case MGSL_IOCSTXIDLE: - ret = set_txidle(info, (int)arg); - break; - case MGSL_IOCTXENABLE: - ret = tx_enable(info, (int)arg); - break; - case MGSL_IOCRXENABLE: - ret = rx_enable(info, (int)arg); - break; - case MGSL_IOCTXABORT: - ret = tx_abort(info); - break; - case MGSL_IOCGSTATS: - ret = get_stats(info, argp); - break; - case MGSL_IOCGIF: - ret = get_interface(info, argp); - break; - case MGSL_IOCSIF: - ret = set_interface(info,(int)arg); - break; - default: - ret = -ENOIOCTLCMD; - } - mutex_unlock(&info->port.mutex); - return ret; -} - -static int get_icount(struct tty_struct *tty, - struct serial_icounter_struct *icount) - -{ - struct slgt_info *info = tty->driver_data; - struct mgsl_icount cnow; /* kernel counter temps */ - unsigned long flags; - - spin_lock_irqsave(&info->lock,flags); - cnow = info->icount; - spin_unlock_irqrestore(&info->lock,flags); - - icount->cts = cnow.cts; - icount->dsr = cnow.dsr; - icount->rng = cnow.rng; - icount->dcd = cnow.dcd; - icount->rx = cnow.rx; - icount->tx = cnow.tx; - icount->frame = cnow.frame; - icount->overrun = cnow.overrun; - icount->parity = cnow.parity; - icount->brk = cnow.brk; - icount->buf_overrun = cnow.buf_overrun; - - return 0; -} - -/* - * support for 32 bit ioctl calls on 64 bit systems - */ -#ifdef CONFIG_COMPAT -static long get_params32(struct slgt_info *info, struct MGSL_PARAMS32 __user *user_params) -{ - struct MGSL_PARAMS32 tmp_params; - - DBGINFO(("%s get_params32\n", info->device_name)); - memset(&tmp_params, 0, sizeof(tmp_params)); - tmp_params.mode = (compat_ulong_t)info->params.mode; - tmp_params.loopback = info->params.loopback; - tmp_params.flags = info->params.flags; - tmp_params.encoding = info->params.encoding; - tmp_params.clock_speed = (compat_ulong_t)info->params.clock_speed; - tmp_params.addr_filter = info->params.addr_filter; - tmp_params.crc_type = info->params.crc_type; - tmp_params.preamble_length = info->params.preamble_length; - tmp_params.preamble = info->params.preamble; - tmp_params.data_rate = (compat_ulong_t)info->params.data_rate; - tmp_params.data_bits = info->params.data_bits; - tmp_params.stop_bits = info->params.stop_bits; - tmp_params.parity = info->params.parity; - if (copy_to_user(user_params, &tmp_params, sizeof(struct MGSL_PARAMS32))) - return -EFAULT; - return 0; -} - -static long set_params32(struct slgt_info *info, struct MGSL_PARAMS32 __user *new_params) -{ - struct MGSL_PARAMS32 tmp_params; - unsigned long flags; - - DBGINFO(("%s set_params32\n", info->device_name)); - if (copy_from_user(&tmp_params, new_params, sizeof(struct MGSL_PARAMS32))) - return -EFAULT; - - spin_lock_irqsave(&info->lock, flags); - if (tmp_params.mode == MGSL_MODE_BASE_CLOCK) { - info->base_clock = tmp_params.clock_speed; - } else { - info->params.mode = tmp_params.mode; - info->params.loopback = tmp_params.loopback; - info->params.flags = tmp_params.flags; - info->params.encoding = tmp_params.encoding; - info->params.clock_speed = tmp_params.clock_speed; - info->params.addr_filter = tmp_params.addr_filter; - info->params.crc_type = tmp_params.crc_type; - info->params.preamble_length = tmp_params.preamble_length; - info->params.preamble = tmp_params.preamble; - info->params.data_rate = tmp_params.data_rate; - info->params.data_bits = tmp_params.data_bits; - info->params.stop_bits = tmp_params.stop_bits; - info->params.parity = tmp_params.parity; - } - spin_unlock_irqrestore(&info->lock, flags); - - program_hw(info); - - return 0; -} - -static long slgt_compat_ioctl(struct tty_struct *tty, - unsigned int cmd, unsigned long arg) -{ - struct slgt_info *info = tty->driver_data; - int rc; - - if (sanity_check(info, tty->name, "compat_ioctl")) - return -ENODEV; - DBGINFO(("%s compat_ioctl() cmd=%08X\n", info->device_name, cmd)); - - switch (cmd) { - case MGSL_IOCSPARAMS32: - rc = set_params32(info, compat_ptr(arg)); - break; - - case MGSL_IOCGPARAMS32: - rc = get_params32(info, compat_ptr(arg)); - break; - - case MGSL_IOCGPARAMS: - case MGSL_IOCSPARAMS: - case MGSL_IOCGTXIDLE: - case MGSL_IOCGSTATS: - case MGSL_IOCWAITEVENT: - case MGSL_IOCGIF: - case MGSL_IOCSGPIO: - case MGSL_IOCGGPIO: - case MGSL_IOCWAITGPIO: - case MGSL_IOCGXSYNC: - case MGSL_IOCGXCTRL: - rc = ioctl(tty, cmd, (unsigned long)compat_ptr(arg)); - break; - default: - rc = ioctl(tty, cmd, arg); - } - DBGINFO(("%s compat_ioctl() cmd=%08X rc=%d\n", info->device_name, cmd, rc)); - return rc; -} -#else -#define slgt_compat_ioctl NULL -#endif /* ifdef CONFIG_COMPAT */ - -/* - * proc fs support - */ -static inline void line_info(struct seq_file *m, struct slgt_info *info) -{ - char stat_buf[30]; - unsigned long flags; - - seq_printf(m, "%s: IO=%08X IRQ=%d MaxFrameSize=%u\n", - info->device_name, info->phys_reg_addr, - info->irq_level, info->max_frame_size); - - /* output current serial signal states */ - spin_lock_irqsave(&info->lock,flags); - get_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); - - stat_buf[0] = 0; - stat_buf[1] = 0; - if (info->signals & SerialSignal_RTS) - strcat(stat_buf, "|RTS"); - if (info->signals & SerialSignal_CTS) - strcat(stat_buf, "|CTS"); - if (info->signals & SerialSignal_DTR) - strcat(stat_buf, "|DTR"); - if (info->signals & SerialSignal_DSR) - strcat(stat_buf, "|DSR"); - if (info->signals & SerialSignal_DCD) - strcat(stat_buf, "|CD"); - if (info->signals & SerialSignal_RI) - strcat(stat_buf, "|RI"); - - if (info->params.mode != MGSL_MODE_ASYNC) { - seq_printf(m, "\tHDLC txok:%d rxok:%d", - info->icount.txok, info->icount.rxok); - if (info->icount.txunder) - seq_printf(m, " txunder:%d", info->icount.txunder); - if (info->icount.txabort) - seq_printf(m, " txabort:%d", info->icount.txabort); - if (info->icount.rxshort) - seq_printf(m, " rxshort:%d", info->icount.rxshort); - if (info->icount.rxlong) - seq_printf(m, " rxlong:%d", info->icount.rxlong); - if (info->icount.rxover) - seq_printf(m, " rxover:%d", info->icount.rxover); - if (info->icount.rxcrc) - seq_printf(m, " rxcrc:%d", info->icount.rxcrc); - } else { - seq_printf(m, "\tASYNC tx:%d rx:%d", - info->icount.tx, info->icount.rx); - if (info->icount.frame) - seq_printf(m, " fe:%d", info->icount.frame); - if (info->icount.parity) - seq_printf(m, " pe:%d", info->icount.parity); - if (info->icount.brk) - seq_printf(m, " brk:%d", info->icount.brk); - if (info->icount.overrun) - seq_printf(m, " oe:%d", info->icount.overrun); - } - - /* Append serial signal status to end */ - seq_printf(m, " %s\n", stat_buf+1); - - seq_printf(m, "\ttxactive=%d bh_req=%d bh_run=%d pending_bh=%x\n", - info->tx_active,info->bh_requested,info->bh_running, - info->pending_bh); -} - -/* Called to print information about devices - */ -static int synclink_gt_proc_show(struct seq_file *m, void *v) -{ - struct slgt_info *info; - - seq_puts(m, "synclink_gt driver\n"); - - info = slgt_device_list; - while( info ) { - line_info(m, info); - info = info->next_device; - } - return 0; -} - -/* - * return count of bytes in transmit buffer - */ -static unsigned int chars_in_buffer(struct tty_struct *tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned int count; - if (sanity_check(info, tty->name, "chars_in_buffer")) - return 0; - count = tbuf_bytes(info); - DBGINFO(("%s chars_in_buffer()=%u\n", info->device_name, count)); - return count; -} - -/* - * signal remote device to throttle send data (our receive data) - */ -static void throttle(struct tty_struct * tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "throttle")) - return; - DBGINFO(("%s throttle\n", info->device_name)); - if (I_IXOFF(tty)) - send_xchar(tty, STOP_CHAR(tty)); - if (C_CRTSCTS(tty)) { - spin_lock_irqsave(&info->lock,flags); - info->signals &= ~SerialSignal_RTS; - set_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); - } -} - -/* - * signal remote device to stop throttling send data (our receive data) - */ -static void unthrottle(struct tty_struct * tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - if (sanity_check(info, tty->name, "unthrottle")) - return; - DBGINFO(("%s unthrottle\n", info->device_name)); - if (I_IXOFF(tty)) { - if (info->x_char) - info->x_char = 0; - else - send_xchar(tty, START_CHAR(tty)); - } - if (C_CRTSCTS(tty)) { - spin_lock_irqsave(&info->lock,flags); - info->signals |= SerialSignal_RTS; - set_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); - } -} - -/* - * set or clear transmit break condition - * break_state -1=set break condition, 0=clear - */ -static int set_break(struct tty_struct *tty, int break_state) -{ - struct slgt_info *info = tty->driver_data; - unsigned short value; - unsigned long flags; - - if (sanity_check(info, tty->name, "set_break")) - return -EINVAL; - DBGINFO(("%s set_break(%d)\n", info->device_name, break_state)); - - spin_lock_irqsave(&info->lock,flags); - value = rd_reg16(info, TCR); - if (break_state == -1) - value |= BIT6; - else - value &= ~BIT6; - wr_reg16(info, TCR, value); - spin_unlock_irqrestore(&info->lock,flags); - return 0; -} - -#if SYNCLINK_GENERIC_HDLC - -/** - * hdlcdev_attach - called by generic HDLC layer when protocol selected (PPP, frame relay, etc.) - * @dev: pointer to network device structure - * @encoding: serial encoding setting - * @parity: FCS setting - * - * Set encoding and frame check sequence (FCS) options. - * - * Return: 0 if success, otherwise error code - */ -static int hdlcdev_attach(struct net_device *dev, unsigned short encoding, - unsigned short parity) -{ - struct slgt_info *info = dev_to_port(dev); - unsigned char new_encoding; - unsigned short new_crctype; - - /* return error if TTY interface open */ - if (info->port.count) - return -EBUSY; - - DBGINFO(("%s hdlcdev_attach\n", info->device_name)); - - switch (encoding) - { - case ENCODING_NRZ: new_encoding = HDLC_ENCODING_NRZ; break; - case ENCODING_NRZI: new_encoding = HDLC_ENCODING_NRZI_SPACE; break; - case ENCODING_FM_MARK: new_encoding = HDLC_ENCODING_BIPHASE_MARK; break; - case ENCODING_FM_SPACE: new_encoding = HDLC_ENCODING_BIPHASE_SPACE; break; - case ENCODING_MANCHESTER: new_encoding = HDLC_ENCODING_BIPHASE_LEVEL; break; - default: return -EINVAL; - } - - switch (parity) - { - case PARITY_NONE: new_crctype = HDLC_CRC_NONE; break; - case PARITY_CRC16_PR1_CCITT: new_crctype = HDLC_CRC_16_CCITT; break; - case PARITY_CRC32_PR1_CCITT: new_crctype = HDLC_CRC_32_CCITT; break; - default: return -EINVAL; - } - - info->params.encoding = new_encoding; - info->params.crc_type = new_crctype; - - /* if network interface up, reprogram hardware */ - if (info->netcount) - program_hw(info); - - return 0; -} - -/** - * hdlcdev_xmit - called by generic HDLC layer to send a frame - * @skb: socket buffer containing HDLC frame - * @dev: pointer to network device structure - */ -static netdev_tx_t hdlcdev_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - struct slgt_info *info = dev_to_port(dev); - unsigned long flags; - - DBGINFO(("%s hdlc_xmit\n", dev->name)); - - if (!skb->len) - return NETDEV_TX_OK; - - /* stop sending until this frame completes */ - netif_stop_queue(dev); - - /* update network statistics */ - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - - /* save start time for transmit timeout detection */ - netif_trans_update(dev); - - spin_lock_irqsave(&info->lock, flags); - tx_load(info, skb->data, skb->len); - spin_unlock_irqrestore(&info->lock, flags); - - /* done with socket buffer, so free it */ - dev_kfree_skb(skb); - - return NETDEV_TX_OK; -} - -/** - * hdlcdev_open - called by network layer when interface enabled - * @dev: pointer to network device structure - * - * Claim resources and initialize hardware. - * - * Return: 0 if success, otherwise error code - */ -static int hdlcdev_open(struct net_device *dev) -{ - struct slgt_info *info = dev_to_port(dev); - int rc; - unsigned long flags; - - DBGINFO(("%s hdlcdev_open\n", dev->name)); - - /* arbitrate between network and tty opens */ - spin_lock_irqsave(&info->netlock, flags); - if (info->port.count != 0 || info->netcount != 0) { - DBGINFO(("%s hdlc_open busy\n", dev->name)); - spin_unlock_irqrestore(&info->netlock, flags); - return -EBUSY; - } - info->netcount=1; - spin_unlock_irqrestore(&info->netlock, flags); - - /* claim resources and init adapter */ - if ((rc = startup_hw(info)) != 0) { - spin_lock_irqsave(&info->netlock, flags); - info->netcount=0; - spin_unlock_irqrestore(&info->netlock, flags); - return rc; - } - - /* generic HDLC layer open processing */ - rc = hdlc_open(dev); - if (rc) { - shutdown_hw(info); - spin_lock_irqsave(&info->netlock, flags); - info->netcount = 0; - spin_unlock_irqrestore(&info->netlock, flags); - return rc; - } - - /* assert RTS and DTR, apply hardware settings */ - info->signals |= SerialSignal_RTS | SerialSignal_DTR; - program_hw(info); - - /* enable network layer transmit */ - netif_trans_update(dev); - netif_start_queue(dev); - - /* inform generic HDLC layer of current DCD status */ - spin_lock_irqsave(&info->lock, flags); - get_gtsignals(info); - spin_unlock_irqrestore(&info->lock, flags); - if (info->signals & SerialSignal_DCD) - netif_carrier_on(dev); - else - netif_carrier_off(dev); - return 0; -} - -/** - * hdlcdev_close - called by network layer when interface is disabled - * @dev: pointer to network device structure - * - * Shutdown hardware and release resources. - * - * Return: 0 if success, otherwise error code - */ -static int hdlcdev_close(struct net_device *dev) -{ - struct slgt_info *info = dev_to_port(dev); - unsigned long flags; - - DBGINFO(("%s hdlcdev_close\n", dev->name)); - - netif_stop_queue(dev); - - /* shutdown adapter and release resources */ - shutdown_hw(info); - - hdlc_close(dev); - - spin_lock_irqsave(&info->netlock, flags); - info->netcount=0; - spin_unlock_irqrestore(&info->netlock, flags); - - return 0; -} - -/** - * hdlcdev_ioctl - called by network layer to process IOCTL call to network device - * @dev: pointer to network device structure - * @ifr: pointer to network interface request structure - * @cmd: IOCTL command code - * - * Return: 0 if success, otherwise error code - */ -static int hdlcdev_ioctl(struct net_device *dev, struct if_settings *ifs) -{ - const size_t size = sizeof(sync_serial_settings); - sync_serial_settings new_line; - sync_serial_settings __user *line = ifs->ifs_ifsu.sync; - struct slgt_info *info = dev_to_port(dev); - unsigned int flags; - - DBGINFO(("%s hdlcdev_ioctl\n", dev->name)); - - /* return error if TTY interface open */ - if (info->port.count) - return -EBUSY; - - memset(&new_line, 0, sizeof(new_line)); - - switch (ifs->type) { - case IF_GET_IFACE: /* return current sync_serial_settings */ - - ifs->type = IF_IFACE_SYNC_SERIAL; - if (ifs->size < size) { - ifs->size = size; /* data size wanted */ - return -ENOBUFS; - } - - flags = info->params.flags & (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_RXC_DPLL | - HDLC_FLAG_RXC_BRG | HDLC_FLAG_RXC_TXCPIN | - HDLC_FLAG_TXC_TXCPIN | HDLC_FLAG_TXC_DPLL | - HDLC_FLAG_TXC_BRG | HDLC_FLAG_TXC_RXCPIN); - - switch (flags){ - case (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_TXCPIN): new_line.clock_type = CLOCK_EXT; break; - case (HDLC_FLAG_RXC_BRG | HDLC_FLAG_TXC_BRG): new_line.clock_type = CLOCK_INT; break; - case (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_BRG): new_line.clock_type = CLOCK_TXINT; break; - case (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_RXCPIN): new_line.clock_type = CLOCK_TXFROMRX; break; - default: new_line.clock_type = CLOCK_DEFAULT; - } - - new_line.clock_rate = info->params.clock_speed; - new_line.loopback = info->params.loopback ? 1:0; - - if (copy_to_user(line, &new_line, size)) - return -EFAULT; - return 0; - - case IF_IFACE_SYNC_SERIAL: /* set sync_serial_settings */ - - if(!capable(CAP_NET_ADMIN)) - return -EPERM; - if (copy_from_user(&new_line, line, size)) - return -EFAULT; - - switch (new_line.clock_type) - { - case CLOCK_EXT: flags = HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_TXCPIN; break; - case CLOCK_TXFROMRX: flags = HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_RXCPIN; break; - case CLOCK_INT: flags = HDLC_FLAG_RXC_BRG | HDLC_FLAG_TXC_BRG; break; - case CLOCK_TXINT: flags = HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_BRG; break; - case CLOCK_DEFAULT: flags = info->params.flags & - (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_RXC_DPLL | - HDLC_FLAG_RXC_BRG | HDLC_FLAG_RXC_TXCPIN | - HDLC_FLAG_TXC_TXCPIN | HDLC_FLAG_TXC_DPLL | - HDLC_FLAG_TXC_BRG | HDLC_FLAG_TXC_RXCPIN); break; - default: return -EINVAL; - } - - if (new_line.loopback != 0 && new_line.loopback != 1) - return -EINVAL; - - info->params.flags &= ~(HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_RXC_DPLL | - HDLC_FLAG_RXC_BRG | HDLC_FLAG_RXC_TXCPIN | - HDLC_FLAG_TXC_TXCPIN | HDLC_FLAG_TXC_DPLL | - HDLC_FLAG_TXC_BRG | HDLC_FLAG_TXC_RXCPIN); - info->params.flags |= flags; - - info->params.loopback = new_line.loopback; - - if (flags & (HDLC_FLAG_RXC_BRG | HDLC_FLAG_TXC_BRG)) - info->params.clock_speed = new_line.clock_rate; - else - info->params.clock_speed = 0; - - /* if network interface up, reprogram hardware */ - if (info->netcount) - program_hw(info); - return 0; - - default: - return hdlc_ioctl(dev, ifs); - } -} - -/** - * hdlcdev_tx_timeout - called by network layer when transmit timeout is detected - * @dev: pointer to network device structure - * @txqueue: unused - */ -static void hdlcdev_tx_timeout(struct net_device *dev, unsigned int txqueue) -{ - struct slgt_info *info = dev_to_port(dev); - unsigned long flags; - - DBGINFO(("%s hdlcdev_tx_timeout\n", dev->name)); - - dev->stats.tx_errors++; - dev->stats.tx_aborted_errors++; - - spin_lock_irqsave(&info->lock,flags); - tx_stop(info); - spin_unlock_irqrestore(&info->lock,flags); - - netif_wake_queue(dev); -} - -/** - * hdlcdev_tx_done - called by device driver when transmit completes - * @info: pointer to device instance information - * - * Reenable network layer transmit if stopped. - */ -static void hdlcdev_tx_done(struct slgt_info *info) -{ - if (netif_queue_stopped(info->netdev)) - netif_wake_queue(info->netdev); -} - -/** - * hdlcdev_rx - called by device driver when frame received - * @info: pointer to device instance information - * @buf: pointer to buffer contianing frame data - * @size: count of data bytes in buf - * - * Pass frame to network layer. - */ -static void hdlcdev_rx(struct slgt_info *info, char *buf, int size) -{ - struct sk_buff *skb = dev_alloc_skb(size); - struct net_device *dev = info->netdev; - - DBGINFO(("%s hdlcdev_rx\n", dev->name)); - - if (skb == NULL) { - DBGERR(("%s: can't alloc skb, drop packet\n", dev->name)); - dev->stats.rx_dropped++; - return; - } - - skb_put_data(skb, buf, size); - - skb->protocol = hdlc_type_trans(skb, dev); - - dev->stats.rx_packets++; - dev->stats.rx_bytes += size; - - netif_rx(skb); -} - -static const struct net_device_ops hdlcdev_ops = { - .ndo_open = hdlcdev_open, - .ndo_stop = hdlcdev_close, - .ndo_start_xmit = hdlc_start_xmit, - .ndo_siocwandev = hdlcdev_ioctl, - .ndo_tx_timeout = hdlcdev_tx_timeout, -}; - -/** - * hdlcdev_init - called by device driver when adding device instance - * @info: pointer to device instance information - * - * Do generic HDLC initialization. - * - * Return: 0 if success, otherwise error code - */ -static int hdlcdev_init(struct slgt_info *info) -{ - int rc; - struct net_device *dev; - hdlc_device *hdlc; - - /* allocate and initialize network and HDLC layer objects */ - - dev = alloc_hdlcdev(info); - if (!dev) { - printk(KERN_ERR "%s hdlc device alloc failure\n", info->device_name); - return -ENOMEM; - } - - /* for network layer reporting purposes only */ - dev->mem_start = info->phys_reg_addr; - dev->mem_end = info->phys_reg_addr + SLGT_REG_SIZE - 1; - dev->irq = info->irq_level; - - /* network layer callbacks and settings */ - dev->netdev_ops = &hdlcdev_ops; - dev->watchdog_timeo = 10 * HZ; - dev->tx_queue_len = 50; - - /* generic HDLC layer callbacks and settings */ - hdlc = dev_to_hdlc(dev); - hdlc->attach = hdlcdev_attach; - hdlc->xmit = hdlcdev_xmit; - - /* register objects with HDLC layer */ - rc = register_hdlc_device(dev); - if (rc) { - printk(KERN_WARNING "%s:unable to register hdlc device\n",__FILE__); - free_netdev(dev); - return rc; - } - - info->netdev = dev; - return 0; -} - -/** - * hdlcdev_exit - called by device driver when removing device instance - * @info: pointer to device instance information - * - * Do generic HDLC cleanup. - */ -static void hdlcdev_exit(struct slgt_info *info) -{ - if (!info->netdev) - return; - unregister_hdlc_device(info->netdev); - free_netdev(info->netdev); - info->netdev = NULL; -} - -#endif /* ifdef CONFIG_HDLC */ - -/* - * get async data from rx DMA buffers - */ -static void rx_async(struct slgt_info *info) -{ - struct mgsl_icount *icount = &info->icount; - unsigned int start, end; - unsigned char *p; - unsigned char status; - struct slgt_desc *bufs = info->rbufs; - int i, count; - int chars = 0; - int stat; - unsigned char ch; - - start = end = info->rbuf_current; - - while(desc_complete(bufs[end])) { - count = desc_count(bufs[end]) - info->rbuf_index; - p = bufs[end].buf + info->rbuf_index; - - DBGISR(("%s rx_async count=%d\n", info->device_name, count)); - DBGDATA(info, p, count, "rx"); - - for(i=0 ; i < count; i+=2, p+=2) { - ch = *p; - icount->rx++; - - stat = 0; - - status = *(p + 1) & (BIT1 + BIT0); - if (status) { - if (status & BIT1) - icount->parity++; - else if (status & BIT0) - icount->frame++; - /* discard char if tty control flags say so */ - if (status & info->ignore_status_mask) - continue; - if (status & BIT1) - stat = TTY_PARITY; - else if (status & BIT0) - stat = TTY_FRAME; - } - tty_insert_flip_char(&info->port, ch, stat); - chars++; - } - - if (i < count) { - /* receive buffer not completed */ - info->rbuf_index += i; - mod_timer(&info->rx_timer, jiffies + 1); - break; - } - - info->rbuf_index = 0; - free_rbufs(info, end, end); - - if (++end == info->rbuf_count) - end = 0; - - /* if entire list searched then no frame available */ - if (end == start) - break; - } - - if (chars) - tty_flip_buffer_push(&info->port); -} - -/* - * return next bottom half action to perform - */ -static int bh_action(struct slgt_info *info) -{ - unsigned long flags; - int rc; - - spin_lock_irqsave(&info->lock,flags); - - if (info->pending_bh & BH_RECEIVE) { - info->pending_bh &= ~BH_RECEIVE; - rc = BH_RECEIVE; - } else if (info->pending_bh & BH_TRANSMIT) { - info->pending_bh &= ~BH_TRANSMIT; - rc = BH_TRANSMIT; - } else if (info->pending_bh & BH_STATUS) { - info->pending_bh &= ~BH_STATUS; - rc = BH_STATUS; - } else { - /* Mark BH routine as complete */ - info->bh_running = false; - info->bh_requested = false; - rc = 0; - } - - spin_unlock_irqrestore(&info->lock,flags); - - return rc; -} - -/* - * perform bottom half processing - */ -static void bh_handler(struct work_struct *work) -{ - struct slgt_info *info = container_of(work, struct slgt_info, task); - int action; - - info->bh_running = true; - - while((action = bh_action(info))) { - switch (action) { - case BH_RECEIVE: - DBGBH(("%s bh receive\n", info->device_name)); - switch(info->params.mode) { - case MGSL_MODE_ASYNC: - rx_async(info); - break; - case MGSL_MODE_HDLC: - while(rx_get_frame(info)); - break; - case MGSL_MODE_RAW: - case MGSL_MODE_MONOSYNC: - case MGSL_MODE_BISYNC: - case MGSL_MODE_XSYNC: - while(rx_get_buf(info)); - break; - } - /* restart receiver if rx DMA buffers exhausted */ - if (info->rx_restart) - rx_start(info); - break; - case BH_TRANSMIT: - bh_transmit(info); - break; - case BH_STATUS: - DBGBH(("%s bh status\n", info->device_name)); - info->ri_chkcount = 0; - info->dsr_chkcount = 0; - info->dcd_chkcount = 0; - info->cts_chkcount = 0; - break; - default: - DBGBH(("%s unknown action\n", info->device_name)); - break; - } - } - DBGBH(("%s bh_handler exit\n", info->device_name)); -} - -static void bh_transmit(struct slgt_info *info) -{ - struct tty_struct *tty = info->port.tty; - - DBGBH(("%s bh_transmit\n", info->device_name)); - if (tty) - tty_wakeup(tty); -} - -static void dsr_change(struct slgt_info *info, unsigned short status) -{ - if (status & BIT3) { - info->signals |= SerialSignal_DSR; - info->input_signal_events.dsr_up++; - } else { - info->signals &= ~SerialSignal_DSR; - info->input_signal_events.dsr_down++; - } - DBGISR(("dsr_change %s signals=%04X\n", info->device_name, info->signals)); - if ((info->dsr_chkcount)++ == IO_PIN_SHUTDOWN_LIMIT) { - slgt_irq_off(info, IRQ_DSR); - return; - } - info->icount.dsr++; - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - info->pending_bh |= BH_STATUS; -} - -static void cts_change(struct slgt_info *info, unsigned short status) -{ - if (status & BIT2) { - info->signals |= SerialSignal_CTS; - info->input_signal_events.cts_up++; - } else { - info->signals &= ~SerialSignal_CTS; - info->input_signal_events.cts_down++; - } - DBGISR(("cts_change %s signals=%04X\n", info->device_name, info->signals)); - if ((info->cts_chkcount)++ == IO_PIN_SHUTDOWN_LIMIT) { - slgt_irq_off(info, IRQ_CTS); - return; - } - info->icount.cts++; - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - info->pending_bh |= BH_STATUS; - - if (tty_port_cts_enabled(&info->port)) { - if (info->port.tty) { - if (info->port.tty->hw_stopped) { - if (info->signals & SerialSignal_CTS) { - info->port.tty->hw_stopped = false; - info->pending_bh |= BH_TRANSMIT; - return; - } - } else { - if (!(info->signals & SerialSignal_CTS)) - info->port.tty->hw_stopped = true; - } - } - } -} - -static void dcd_change(struct slgt_info *info, unsigned short status) -{ - if (status & BIT1) { - info->signals |= SerialSignal_DCD; - info->input_signal_events.dcd_up++; - } else { - info->signals &= ~SerialSignal_DCD; - info->input_signal_events.dcd_down++; - } - DBGISR(("dcd_change %s signals=%04X\n", info->device_name, info->signals)); - if ((info->dcd_chkcount)++ == IO_PIN_SHUTDOWN_LIMIT) { - slgt_irq_off(info, IRQ_DCD); - return; - } - info->icount.dcd++; -#if SYNCLINK_GENERIC_HDLC - if (info->netcount) { - if (info->signals & SerialSignal_DCD) - netif_carrier_on(info->netdev); - else - netif_carrier_off(info->netdev); - } -#endif - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - info->pending_bh |= BH_STATUS; - - if (tty_port_check_carrier(&info->port)) { - if (info->signals & SerialSignal_DCD) - wake_up_interruptible(&info->port.open_wait); - else { - if (info->port.tty) - tty_hangup(info->port.tty); - } - } -} - -static void ri_change(struct slgt_info *info, unsigned short status) -{ - if (status & BIT0) { - info->signals |= SerialSignal_RI; - info->input_signal_events.ri_up++; - } else { - info->signals &= ~SerialSignal_RI; - info->input_signal_events.ri_down++; - } - DBGISR(("ri_change %s signals=%04X\n", info->device_name, info->signals)); - if ((info->ri_chkcount)++ == IO_PIN_SHUTDOWN_LIMIT) { - slgt_irq_off(info, IRQ_RI); - return; - } - info->icount.rng++; - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - info->pending_bh |= BH_STATUS; -} - -static void isr_rxdata(struct slgt_info *info) -{ - unsigned int count = info->rbuf_fill_count; - unsigned int i = info->rbuf_fill_index; - unsigned short reg; - - while (rd_reg16(info, SSR) & IRQ_RXDATA) { - reg = rd_reg16(info, RDR); - DBGISR(("isr_rxdata %s RDR=%04X\n", info->device_name, reg)); - if (desc_complete(info->rbufs[i])) { - /* all buffers full */ - rx_stop(info); - info->rx_restart = true; - continue; - } - info->rbufs[i].buf[count++] = (unsigned char)reg; - /* async mode saves status byte to buffer for each data byte */ - if (info->params.mode == MGSL_MODE_ASYNC) - info->rbufs[i].buf[count++] = (unsigned char)(reg >> 8); - if (count == info->rbuf_fill_level || (reg & BIT10)) { - /* buffer full or end of frame */ - set_desc_count(info->rbufs[i], count); - set_desc_status(info->rbufs[i], BIT15 | (reg >> 8)); - info->rbuf_fill_count = count = 0; - if (++i == info->rbuf_count) - i = 0; - info->pending_bh |= BH_RECEIVE; - } - } - - info->rbuf_fill_index = i; - info->rbuf_fill_count = count; -} - -static void isr_serial(struct slgt_info *info) -{ - unsigned short status = rd_reg16(info, SSR); - - DBGISR(("%s isr_serial status=%04X\n", info->device_name, status)); - - wr_reg16(info, SSR, status); /* clear pending */ - - info->irq_occurred = true; - - if (info->params.mode == MGSL_MODE_ASYNC) { - if (status & IRQ_TXIDLE) { - if (info->tx_active) - isr_txeom(info, status); - } - if (info->rx_pio && (status & IRQ_RXDATA)) - isr_rxdata(info); - if ((status & IRQ_RXBREAK) && (status & RXBREAK)) { - info->icount.brk++; - /* process break detection if tty control allows */ - if (info->port.tty) { - if (!(status & info->ignore_status_mask)) { - if (info->read_status_mask & MASK_BREAK) { - tty_insert_flip_char(&info->port, 0, TTY_BREAK); - if (info->port.flags & ASYNC_SAK) - do_SAK(info->port.tty); - } - } - } - } - } else { - if (status & (IRQ_TXIDLE + IRQ_TXUNDER)) - isr_txeom(info, status); - if (info->rx_pio && (status & IRQ_RXDATA)) - isr_rxdata(info); - if (status & IRQ_RXIDLE) { - if (status & RXIDLE) - info->icount.rxidle++; - else - info->icount.exithunt++; - wake_up_interruptible(&info->event_wait_q); - } - - if (status & IRQ_RXOVER) - rx_start(info); - } - - if (status & IRQ_DSR) - dsr_change(info, status); - if (status & IRQ_CTS) - cts_change(info, status); - if (status & IRQ_DCD) - dcd_change(info, status); - if (status & IRQ_RI) - ri_change(info, status); -} - -static void isr_rdma(struct slgt_info *info) -{ - unsigned int status = rd_reg32(info, RDCSR); - - DBGISR(("%s isr_rdma status=%08x\n", info->device_name, status)); - - /* RDCSR (rx DMA control/status) - * - * 31..07 reserved - * 06 save status byte to DMA buffer - * 05 error - * 04 eol (end of list) - * 03 eob (end of buffer) - * 02 IRQ enable - * 01 reset - * 00 enable - */ - wr_reg32(info, RDCSR, status); /* clear pending */ - - if (status & (BIT5 + BIT4)) { - DBGISR(("%s isr_rdma rx_restart=1\n", info->device_name)); - info->rx_restart = true; - } - info->pending_bh |= BH_RECEIVE; -} - -static void isr_tdma(struct slgt_info *info) -{ - unsigned int status = rd_reg32(info, TDCSR); - - DBGISR(("%s isr_tdma status=%08x\n", info->device_name, status)); - - /* TDCSR (tx DMA control/status) - * - * 31..06 reserved - * 05 error - * 04 eol (end of list) - * 03 eob (end of buffer) - * 02 IRQ enable - * 01 reset - * 00 enable - */ - wr_reg32(info, TDCSR, status); /* clear pending */ - - if (status & (BIT5 + BIT4 + BIT3)) { - // another transmit buffer has completed - // run bottom half to get more send data from user - info->pending_bh |= BH_TRANSMIT; - } -} - -/* - * return true if there are unsent tx DMA buffers, otherwise false - * - * if there are unsent buffers then info->tbuf_start - * is set to index of first unsent buffer - */ -static bool unsent_tbufs(struct slgt_info *info) -{ - unsigned int i = info->tbuf_current; - bool rc = false; - - /* - * search backwards from last loaded buffer (precedes tbuf_current) - * for first unsent buffer (desc_count > 0) - */ - - do { - if (i) - i--; - else - i = info->tbuf_count - 1; - if (!desc_count(info->tbufs[i])) - break; - info->tbuf_start = i; - rc = true; - } while (i != info->tbuf_current); - - return rc; -} - -static void isr_txeom(struct slgt_info *info, unsigned short status) -{ - DBGISR(("%s txeom status=%04x\n", info->device_name, status)); - - slgt_irq_off(info, IRQ_TXDATA + IRQ_TXIDLE + IRQ_TXUNDER); - tdma_reset(info); - if (status & IRQ_TXUNDER) { - unsigned short val = rd_reg16(info, TCR); - wr_reg16(info, TCR, (unsigned short)(val | BIT2)); /* set reset bit */ - wr_reg16(info, TCR, val); /* clear reset bit */ - } - - if (info->tx_active) { - if (info->params.mode != MGSL_MODE_ASYNC) { - if (status & IRQ_TXUNDER) - info->icount.txunder++; - else if (status & IRQ_TXIDLE) - info->icount.txok++; - } - - if (unsent_tbufs(info)) { - tx_start(info); - update_tx_timer(info); - return; - } - info->tx_active = false; - - timer_delete(&info->tx_timer); - - if (info->params.mode != MGSL_MODE_ASYNC && info->drop_rts_on_tx_done) { - info->signals &= ~SerialSignal_RTS; - info->drop_rts_on_tx_done = false; - set_gtsignals(info); - } - -#if SYNCLINK_GENERIC_HDLC - if (info->netcount) - hdlcdev_tx_done(info); - else -#endif - { - if (info->port.tty && (info->port.tty->flow.stopped || info->port.tty->hw_stopped)) { - tx_stop(info); - return; - } - info->pending_bh |= BH_TRANSMIT; - } - } -} - -static void isr_gpio(struct slgt_info *info, unsigned int changed, unsigned int state) -{ - struct cond_wait *w, *prev; - - /* wake processes waiting for specific transitions */ - for (w = info->gpio_wait_q, prev = NULL ; w != NULL ; w = w->next) { - if (w->data & changed) { - w->data = state; - wake_up_interruptible(&w->q); - if (prev != NULL) - prev->next = w->next; - else - info->gpio_wait_q = w->next; - } else - prev = w; - } -} - -/* interrupt service routine - * - * irq interrupt number - * dev_id device ID supplied during interrupt registration - */ -static irqreturn_t slgt_interrupt(int dummy, void *dev_id) -{ - struct slgt_info *info = dev_id; - unsigned int gsr; - unsigned int i; - - DBGISR(("slgt_interrupt irq=%d entry\n", info->irq_level)); - - while((gsr = rd_reg32(info, GSR) & 0xffffff00)) { - DBGISR(("%s gsr=%08x\n", info->device_name, gsr)); - info->irq_occurred = true; - for(i=0; i < info->port_count ; i++) { - if (info->port_array[i] == NULL) - continue; - spin_lock(&info->port_array[i]->lock); - if (gsr & (BIT8 << i)) - isr_serial(info->port_array[i]); - if (gsr & (BIT16 << (i*2))) - isr_rdma(info->port_array[i]); - if (gsr & (BIT17 << (i*2))) - isr_tdma(info->port_array[i]); - spin_unlock(&info->port_array[i]->lock); - } - } - - if (info->gpio_present) { - unsigned int state; - unsigned int changed; - spin_lock(&info->lock); - while ((changed = rd_reg32(info, IOSR)) != 0) { - DBGISR(("%s iosr=%08x\n", info->device_name, changed)); - /* read latched state of GPIO signals */ - state = rd_reg32(info, IOVR); - /* clear pending GPIO interrupt bits */ - wr_reg32(info, IOSR, changed); - for (i=0 ; i < info->port_count ; i++) { - if (info->port_array[i] != NULL) - isr_gpio(info->port_array[i], changed, state); - } - } - spin_unlock(&info->lock); - } - - for(i=0; i < info->port_count ; i++) { - struct slgt_info *port = info->port_array[i]; - if (port == NULL) - continue; - spin_lock(&port->lock); - if ((port->port.count || port->netcount) && - port->pending_bh && !port->bh_running && - !port->bh_requested) { - DBGISR(("%s bh queued\n", port->device_name)); - schedule_work(&port->task); - port->bh_requested = true; - } - spin_unlock(&port->lock); - } - - DBGISR(("slgt_interrupt irq=%d exit\n", info->irq_level)); - return IRQ_HANDLED; -} - -static int startup_hw(struct slgt_info *info) -{ - DBGINFO(("%s startup\n", info->device_name)); - - if (tty_port_initialized(&info->port)) - return 0; - - if (!info->tx_buf) { - info->tx_buf = kmalloc(info->max_frame_size, GFP_KERNEL); - if (!info->tx_buf) { - DBGERR(("%s can't allocate tx buffer\n", info->device_name)); - return -ENOMEM; - } - } - - info->pending_bh = 0; - - memset(&info->icount, 0, sizeof(info->icount)); - - /* program hardware for current parameters */ - change_params(info); - - if (info->port.tty) - clear_bit(TTY_IO_ERROR, &info->port.tty->flags); - - tty_port_set_initialized(&info->port, true); - - return 0; -} - -/* - * called by close() and hangup() to shutdown hardware - */ -static void shutdown_hw(struct slgt_info *info) -{ - unsigned long flags; - - if (!tty_port_initialized(&info->port)) - return; - - DBGINFO(("%s shutdown\n", info->device_name)); - - /* clear status wait queue because status changes */ - /* can't happen after shutting down the hardware */ - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - - timer_delete_sync(&info->tx_timer); - timer_delete_sync(&info->rx_timer); - - kfree(info->tx_buf); - info->tx_buf = NULL; - - spin_lock_irqsave(&info->lock,flags); - - tx_stop(info); - rx_stop(info); - - slgt_irq_off(info, IRQ_ALL | IRQ_MASTER); - - if (!info->port.tty || info->port.tty->termios.c_cflag & HUPCL) { - info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_gtsignals(info); - } - - flush_cond_wait(&info->gpio_wait_q); - - spin_unlock_irqrestore(&info->lock,flags); - - if (info->port.tty) - set_bit(TTY_IO_ERROR, &info->port.tty->flags); - - tty_port_set_initialized(&info->port, false); -} - -static void program_hw(struct slgt_info *info) -{ - unsigned long flags; - - spin_lock_irqsave(&info->lock,flags); - - rx_stop(info); - tx_stop(info); - - if (info->params.mode != MGSL_MODE_ASYNC || - info->netcount) - sync_mode(info); - else - async_mode(info); - - set_gtsignals(info); - - info->dcd_chkcount = 0; - info->cts_chkcount = 0; - info->ri_chkcount = 0; - info->dsr_chkcount = 0; - - slgt_irq_on(info, IRQ_DCD | IRQ_CTS | IRQ_DSR | IRQ_RI); - get_gtsignals(info); - - if (info->netcount || - (info->port.tty && info->port.tty->termios.c_cflag & CREAD)) - rx_start(info); - - spin_unlock_irqrestore(&info->lock,flags); -} - -/* - * reconfigure adapter based on new parameters - */ -static void change_params(struct slgt_info *info) -{ - unsigned cflag; - int bits_per_char; - - if (!info->port.tty) - return; - DBGINFO(("%s change_params\n", info->device_name)); - - cflag = info->port.tty->termios.c_cflag; - - /* if B0 rate (hangup) specified then negate RTS and DTR */ - /* otherwise assert RTS and DTR */ - if (cflag & CBAUD) - info->signals |= SerialSignal_RTS | SerialSignal_DTR; - else - info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - - /* byte size and parity */ - - info->params.data_bits = tty_get_char_size(cflag); - info->params.stop_bits = (cflag & CSTOPB) ? 2 : 1; - - if (cflag & PARENB) - info->params.parity = (cflag & PARODD) ? ASYNC_PARITY_ODD : ASYNC_PARITY_EVEN; - else - info->params.parity = ASYNC_PARITY_NONE; - - /* calculate number of jiffies to transmit a full - * FIFO (32 bytes) at specified data rate - */ - bits_per_char = info->params.data_bits + - info->params.stop_bits + 1; - - info->params.data_rate = tty_get_baud_rate(info->port.tty); - - if (info->params.data_rate) { - info->timeout = (32*HZ*bits_per_char) / - info->params.data_rate; - } - info->timeout += HZ/50; /* Add .02 seconds of slop */ - - tty_port_set_cts_flow(&info->port, cflag & CRTSCTS); - tty_port_set_check_carrier(&info->port, ~cflag & CLOCAL); - - /* process tty input control flags */ - - info->read_status_mask = IRQ_RXOVER; - if (I_INPCK(info->port.tty)) - info->read_status_mask |= MASK_PARITY | MASK_FRAMING; - if (I_BRKINT(info->port.tty) || I_PARMRK(info->port.tty)) - info->read_status_mask |= MASK_BREAK; - if (I_IGNPAR(info->port.tty)) - info->ignore_status_mask |= MASK_PARITY | MASK_FRAMING; - if (I_IGNBRK(info->port.tty)) { - info->ignore_status_mask |= MASK_BREAK; - /* If ignoring parity and break indicators, ignore - * overruns too. (For real raw support). - */ - if (I_IGNPAR(info->port.tty)) - info->ignore_status_mask |= MASK_OVERRUN; - } - - program_hw(info); -} - -static int get_stats(struct slgt_info *info, struct mgsl_icount __user *user_icount) -{ - DBGINFO(("%s get_stats\n", info->device_name)); - if (!user_icount) { - memset(&info->icount, 0, sizeof(info->icount)); - } else { - if (copy_to_user(user_icount, &info->icount, sizeof(struct mgsl_icount))) - return -EFAULT; - } - return 0; -} - -static int get_params(struct slgt_info *info, MGSL_PARAMS __user *user_params) -{ - DBGINFO(("%s get_params\n", info->device_name)); - if (copy_to_user(user_params, &info->params, sizeof(MGSL_PARAMS))) - return -EFAULT; - return 0; -} - -static int set_params(struct slgt_info *info, MGSL_PARAMS __user *new_params) -{ - unsigned long flags; - MGSL_PARAMS tmp_params; - - DBGINFO(("%s set_params\n", info->device_name)); - if (copy_from_user(&tmp_params, new_params, sizeof(MGSL_PARAMS))) - return -EFAULT; - - spin_lock_irqsave(&info->lock, flags); - if (tmp_params.mode == MGSL_MODE_BASE_CLOCK) - info->base_clock = tmp_params.clock_speed; - else - memcpy(&info->params, &tmp_params, sizeof(MGSL_PARAMS)); - spin_unlock_irqrestore(&info->lock, flags); - - program_hw(info); - - return 0; -} - -static int get_txidle(struct slgt_info *info, int __user *idle_mode) -{ - DBGINFO(("%s get_txidle=%d\n", info->device_name, info->idle_mode)); - if (put_user(info->idle_mode, idle_mode)) - return -EFAULT; - return 0; -} - -static int set_txidle(struct slgt_info *info, int idle_mode) -{ - unsigned long flags; - DBGINFO(("%s set_txidle(%d)\n", info->device_name, idle_mode)); - spin_lock_irqsave(&info->lock,flags); - info->idle_mode = idle_mode; - if (info->params.mode != MGSL_MODE_ASYNC) - tx_set_idle(info); - spin_unlock_irqrestore(&info->lock,flags); - return 0; -} - -static int tx_enable(struct slgt_info *info, int enable) -{ - unsigned long flags; - DBGINFO(("%s tx_enable(%d)\n", info->device_name, enable)); - spin_lock_irqsave(&info->lock,flags); - if (enable) { - if (!info->tx_enabled) - tx_start(info); - } else { - if (info->tx_enabled) - tx_stop(info); - } - spin_unlock_irqrestore(&info->lock,flags); - return 0; -} - -/* - * abort transmit HDLC frame - */ -static int tx_abort(struct slgt_info *info) -{ - unsigned long flags; - DBGINFO(("%s tx_abort\n", info->device_name)); - spin_lock_irqsave(&info->lock,flags); - tdma_reset(info); - spin_unlock_irqrestore(&info->lock,flags); - return 0; -} - -static int rx_enable(struct slgt_info *info, int enable) -{ - unsigned long flags; - unsigned int rbuf_fill_level; - DBGINFO(("%s rx_enable(%08x)\n", info->device_name, enable)); - spin_lock_irqsave(&info->lock,flags); - /* - * enable[31..16] = receive DMA buffer fill level - * 0 = noop (leave fill level unchanged) - * fill level must be multiple of 4 and <= buffer size - */ - rbuf_fill_level = ((unsigned int)enable) >> 16; - if (rbuf_fill_level) { - if ((rbuf_fill_level > DMABUFSIZE) || (rbuf_fill_level % 4)) { - spin_unlock_irqrestore(&info->lock, flags); - return -EINVAL; - } - info->rbuf_fill_level = rbuf_fill_level; - if (rbuf_fill_level < 128) - info->rx_pio = 1; /* PIO mode */ - else - info->rx_pio = 0; /* DMA mode */ - rx_stop(info); /* restart receiver to use new fill level */ - } - - /* - * enable[1..0] = receiver enable command - * 0 = disable - * 1 = enable - * 2 = enable or force hunt mode if already enabled - */ - enable &= 3; - if (enable) { - if (!info->rx_enabled) - rx_start(info); - else if (enable == 2) { - /* force hunt mode (write 1 to RCR[3]) */ - wr_reg16(info, RCR, rd_reg16(info, RCR) | BIT3); - } - } else { - if (info->rx_enabled) - rx_stop(info); - } - spin_unlock_irqrestore(&info->lock,flags); - return 0; -} - -/* - * wait for specified event to occur - */ -static int wait_mgsl_event(struct slgt_info *info, int __user *mask_ptr) -{ - unsigned long flags; - int s; - int rc=0; - struct mgsl_icount cprev, cnow; - int events; - int mask; - struct _input_signal_events oldsigs, newsigs; - DECLARE_WAITQUEUE(wait, current); - - if (get_user(mask, mask_ptr)) - return -EFAULT; - - DBGINFO(("%s wait_mgsl_event(%d)\n", info->device_name, mask)); - - spin_lock_irqsave(&info->lock,flags); - - /* return immediately if state matches requested events */ - get_gtsignals(info); - s = info->signals; - - events = mask & - ( ((s & SerialSignal_DSR) ? MgslEvent_DsrActive:MgslEvent_DsrInactive) + - ((s & SerialSignal_DCD) ? MgslEvent_DcdActive:MgslEvent_DcdInactive) + - ((s & SerialSignal_CTS) ? MgslEvent_CtsActive:MgslEvent_CtsInactive) + - ((s & SerialSignal_RI) ? MgslEvent_RiActive :MgslEvent_RiInactive) ); - if (events) { - spin_unlock_irqrestore(&info->lock,flags); - goto exit; - } - - /* save current irq counts */ - cprev = info->icount; - oldsigs = info->input_signal_events; - - /* enable hunt and idle irqs if needed */ - if (mask & (MgslEvent_ExitHuntMode+MgslEvent_IdleReceived)) { - unsigned short val = rd_reg16(info, SCR); - if (!(val & IRQ_RXIDLE)) - wr_reg16(info, SCR, (unsigned short)(val | IRQ_RXIDLE)); - } - - set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&info->event_wait_q, &wait); - - spin_unlock_irqrestore(&info->lock,flags); - - for(;;) { - schedule(); - if (signal_pending(current)) { - rc = -ERESTARTSYS; - break; - } - - /* get current irq counts */ - spin_lock_irqsave(&info->lock,flags); - cnow = info->icount; - newsigs = info->input_signal_events; - set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irqrestore(&info->lock,flags); - - /* if no change, wait aborted for some reason */ - if (newsigs.dsr_up == oldsigs.dsr_up && - newsigs.dsr_down == oldsigs.dsr_down && - newsigs.dcd_up == oldsigs.dcd_up && - newsigs.dcd_down == oldsigs.dcd_down && - newsigs.cts_up == oldsigs.cts_up && - newsigs.cts_down == oldsigs.cts_down && - newsigs.ri_up == oldsigs.ri_up && - newsigs.ri_down == oldsigs.ri_down && - cnow.exithunt == cprev.exithunt && - cnow.rxidle == cprev.rxidle) { - rc = -EIO; - break; - } - - events = mask & - ( (newsigs.dsr_up != oldsigs.dsr_up ? MgslEvent_DsrActive:0) + - (newsigs.dsr_down != oldsigs.dsr_down ? MgslEvent_DsrInactive:0) + - (newsigs.dcd_up != oldsigs.dcd_up ? MgslEvent_DcdActive:0) + - (newsigs.dcd_down != oldsigs.dcd_down ? MgslEvent_DcdInactive:0) + - (newsigs.cts_up != oldsigs.cts_up ? MgslEvent_CtsActive:0) + - (newsigs.cts_down != oldsigs.cts_down ? MgslEvent_CtsInactive:0) + - (newsigs.ri_up != oldsigs.ri_up ? MgslEvent_RiActive:0) + - (newsigs.ri_down != oldsigs.ri_down ? MgslEvent_RiInactive:0) + - (cnow.exithunt != cprev.exithunt ? MgslEvent_ExitHuntMode:0) + - (cnow.rxidle != cprev.rxidle ? MgslEvent_IdleReceived:0) ); - if (events) - break; - - cprev = cnow; - oldsigs = newsigs; - } - - remove_wait_queue(&info->event_wait_q, &wait); - set_current_state(TASK_RUNNING); - - - if (mask & (MgslEvent_ExitHuntMode + MgslEvent_IdleReceived)) { - spin_lock_irqsave(&info->lock,flags); - if (!waitqueue_active(&info->event_wait_q)) { - /* disable enable exit hunt mode/idle rcvd IRQs */ - wr_reg16(info, SCR, - (unsigned short)(rd_reg16(info, SCR) & ~IRQ_RXIDLE)); - } - spin_unlock_irqrestore(&info->lock,flags); - } -exit: - if (rc == 0) - rc = put_user(events, mask_ptr); - return rc; -} - -static int get_interface(struct slgt_info *info, int __user *if_mode) -{ - DBGINFO(("%s get_interface=%x\n", info->device_name, info->if_mode)); - if (put_user(info->if_mode, if_mode)) - return -EFAULT; - return 0; -} - -static int set_interface(struct slgt_info *info, int if_mode) -{ - unsigned long flags; - unsigned short val; - - DBGINFO(("%s set_interface=%x)\n", info->device_name, if_mode)); - spin_lock_irqsave(&info->lock,flags); - info->if_mode = if_mode; - - msc_set_vcr(info); - - /* TCR (tx control) 07 1=RTS driver control */ - val = rd_reg16(info, TCR); - if (info->if_mode & MGSL_INTERFACE_RTS_EN) - val |= BIT7; - else - val &= ~BIT7; - wr_reg16(info, TCR, val); - - spin_unlock_irqrestore(&info->lock,flags); - return 0; -} - -static int get_xsync(struct slgt_info *info, int __user *xsync) -{ - DBGINFO(("%s get_xsync=%x\n", info->device_name, info->xsync)); - if (put_user(info->xsync, xsync)) - return -EFAULT; - return 0; -} - -/* - * set extended sync pattern (1 to 4 bytes) for extended sync mode - * - * sync pattern is contained in least significant bytes of value - * most significant byte of sync pattern is oldest (1st sent/detected) - */ -static int set_xsync(struct slgt_info *info, int xsync) -{ - unsigned long flags; - - DBGINFO(("%s set_xsync=%x)\n", info->device_name, xsync)); - spin_lock_irqsave(&info->lock, flags); - info->xsync = xsync; - wr_reg32(info, XSR, xsync); - spin_unlock_irqrestore(&info->lock, flags); - return 0; -} - -static int get_xctrl(struct slgt_info *info, int __user *xctrl) -{ - DBGINFO(("%s get_xctrl=%x\n", info->device_name, info->xctrl)); - if (put_user(info->xctrl, xctrl)) - return -EFAULT; - return 0; -} - -/* - * set extended control options - * - * xctrl[31:19] reserved, must be zero - * xctrl[18:17] extended sync pattern length in bytes - * 00 = 1 byte in xsr[7:0] - * 01 = 2 bytes in xsr[15:0] - * 10 = 3 bytes in xsr[23:0] - * 11 = 4 bytes in xsr[31:0] - * xctrl[16] 1 = enable terminal count, 0=disabled - * xctrl[15:0] receive terminal count for fixed length packets - * value is count minus one (0 = 1 byte packet) - * when terminal count is reached, receiver - * automatically returns to hunt mode and receive - * FIFO contents are flushed to DMA buffers with - * end of frame (EOF) status - */ -static int set_xctrl(struct slgt_info *info, int xctrl) -{ - unsigned long flags; - - DBGINFO(("%s set_xctrl=%x)\n", info->device_name, xctrl)); - spin_lock_irqsave(&info->lock, flags); - info->xctrl = xctrl; - wr_reg32(info, XCR, xctrl); - spin_unlock_irqrestore(&info->lock, flags); - return 0; -} - -/* - * set general purpose IO pin state and direction - * - * user_gpio fields: - * state each bit indicates a pin state - * smask set bit indicates pin state to set - * dir each bit indicates a pin direction (0=input, 1=output) - * dmask set bit indicates pin direction to set - */ -static int set_gpio(struct slgt_info *info, struct gpio_desc __user *user_gpio) -{ - unsigned long flags; - struct gpio_desc gpio; - __u32 data; - - if (!info->gpio_present) - return -EINVAL; - if (copy_from_user(&gpio, user_gpio, sizeof(gpio))) - return -EFAULT; - DBGINFO(("%s set_gpio state=%08x smask=%08x dir=%08x dmask=%08x\n", - info->device_name, gpio.state, gpio.smask, - gpio.dir, gpio.dmask)); - - spin_lock_irqsave(&info->port_array[0]->lock, flags); - if (gpio.dmask) { - data = rd_reg32(info, IODR); - data |= gpio.dmask & gpio.dir; - data &= ~(gpio.dmask & ~gpio.dir); - wr_reg32(info, IODR, data); - } - if (gpio.smask) { - data = rd_reg32(info, IOVR); - data |= gpio.smask & gpio.state; - data &= ~(gpio.smask & ~gpio.state); - wr_reg32(info, IOVR, data); - } - spin_unlock_irqrestore(&info->port_array[0]->lock, flags); - - return 0; -} - -/* - * get general purpose IO pin state and direction - */ -static int get_gpio(struct slgt_info *info, struct gpio_desc __user *user_gpio) -{ - struct gpio_desc gpio; - if (!info->gpio_present) - return -EINVAL; - gpio.state = rd_reg32(info, IOVR); - gpio.smask = 0xffffffff; - gpio.dir = rd_reg32(info, IODR); - gpio.dmask = 0xffffffff; - if (copy_to_user(user_gpio, &gpio, sizeof(gpio))) - return -EFAULT; - DBGINFO(("%s get_gpio state=%08x dir=%08x\n", - info->device_name, gpio.state, gpio.dir)); - return 0; -} - -/* - * conditional wait facility - */ -static void init_cond_wait(struct cond_wait *w, unsigned int data) -{ - init_waitqueue_head(&w->q); - init_waitqueue_entry(&w->wait, current); - w->data = data; -} - -static void add_cond_wait(struct cond_wait **head, struct cond_wait *w) -{ - set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&w->q, &w->wait); - w->next = *head; - *head = w; -} - -static void remove_cond_wait(struct cond_wait **head, struct cond_wait *cw) -{ - struct cond_wait *w, *prev; - remove_wait_queue(&cw->q, &cw->wait); - set_current_state(TASK_RUNNING); - for (w = *head, prev = NULL ; w != NULL ; prev = w, w = w->next) { - if (w == cw) { - if (prev != NULL) - prev->next = w->next; - else - *head = w->next; - break; - } - } -} - -static void flush_cond_wait(struct cond_wait **head) -{ - while (*head != NULL) { - wake_up_interruptible(&(*head)->q); - *head = (*head)->next; - } -} - -/* - * wait for general purpose I/O pin(s) to enter specified state - * - * user_gpio fields: - * state - bit indicates target pin state - * smask - set bit indicates watched pin - * - * The wait ends when at least one watched pin enters the specified - * state. When 0 (no error) is returned, user_gpio->state is set to the - * state of all GPIO pins when the wait ends. - * - * Note: Each pin may be a dedicated input, dedicated output, or - * configurable input/output. The number and configuration of pins - * varies with the specific adapter model. Only input pins (dedicated - * or configured) can be monitored with this function. - */ -static int wait_gpio(struct slgt_info *info, struct gpio_desc __user *user_gpio) -{ - unsigned long flags; - int rc = 0; - struct gpio_desc gpio; - struct cond_wait wait; - u32 state; - - if (!info->gpio_present) - return -EINVAL; - if (copy_from_user(&gpio, user_gpio, sizeof(gpio))) - return -EFAULT; - DBGINFO(("%s wait_gpio() state=%08x smask=%08x\n", - info->device_name, gpio.state, gpio.smask)); - /* ignore output pins identified by set IODR bit */ - if ((gpio.smask &= ~rd_reg32(info, IODR)) == 0) - return -EINVAL; - init_cond_wait(&wait, gpio.smask); - - spin_lock_irqsave(&info->port_array[0]->lock, flags); - /* enable interrupts for watched pins */ - wr_reg32(info, IOER, rd_reg32(info, IOER) | gpio.smask); - /* get current pin states */ - state = rd_reg32(info, IOVR); - - if (gpio.smask & ~(state ^ gpio.state)) { - /* already in target state */ - gpio.state = state; - } else { - /* wait for target state */ - add_cond_wait(&info->gpio_wait_q, &wait); - spin_unlock_irqrestore(&info->port_array[0]->lock, flags); - schedule(); - if (signal_pending(current)) - rc = -ERESTARTSYS; - else - gpio.state = wait.data; - spin_lock_irqsave(&info->port_array[0]->lock, flags); - remove_cond_wait(&info->gpio_wait_q, &wait); - } - - /* disable all GPIO interrupts if no waiting processes */ - if (info->gpio_wait_q == NULL) - wr_reg32(info, IOER, 0); - spin_unlock_irqrestore(&info->port_array[0]->lock, flags); - - if ((rc == 0) && copy_to_user(user_gpio, &gpio, sizeof(gpio))) - rc = -EFAULT; - return rc; -} - -static int modem_input_wait(struct slgt_info *info,int arg) -{ - unsigned long flags; - int rc; - struct mgsl_icount cprev, cnow; - DECLARE_WAITQUEUE(wait, current); - - /* save current irq counts */ - spin_lock_irqsave(&info->lock,flags); - cprev = info->icount; - add_wait_queue(&info->status_event_wait_q, &wait); - set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irqrestore(&info->lock,flags); - - for(;;) { - schedule(); - if (signal_pending(current)) { - rc = -ERESTARTSYS; - break; - } - - /* get new irq counts */ - spin_lock_irqsave(&info->lock,flags); - cnow = info->icount; - set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irqrestore(&info->lock,flags); - - /* if no change, wait aborted for some reason */ - if (cnow.rng == cprev.rng && cnow.dsr == cprev.dsr && - cnow.dcd == cprev.dcd && cnow.cts == cprev.cts) { - rc = -EIO; - break; - } - - /* check for change in caller specified modem input */ - if ((arg & TIOCM_RNG && cnow.rng != cprev.rng) || - (arg & TIOCM_DSR && cnow.dsr != cprev.dsr) || - (arg & TIOCM_CD && cnow.dcd != cprev.dcd) || - (arg & TIOCM_CTS && cnow.cts != cprev.cts)) { - rc = 0; - break; - } - - cprev = cnow; - } - remove_wait_queue(&info->status_event_wait_q, &wait); - set_current_state(TASK_RUNNING); - return rc; -} - -/* - * return state of serial control and status signals - */ -static int tiocmget(struct tty_struct *tty) -{ - struct slgt_info *info = tty->driver_data; - unsigned int result; - unsigned long flags; - - spin_lock_irqsave(&info->lock,flags); - get_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); - - result = ((info->signals & SerialSignal_RTS) ? TIOCM_RTS:0) + - ((info->signals & SerialSignal_DTR) ? TIOCM_DTR:0) + - ((info->signals & SerialSignal_DCD) ? TIOCM_CAR:0) + - ((info->signals & SerialSignal_RI) ? TIOCM_RNG:0) + - ((info->signals & SerialSignal_DSR) ? TIOCM_DSR:0) + - ((info->signals & SerialSignal_CTS) ? TIOCM_CTS:0); - - DBGINFO(("%s tiocmget value=%08X\n", info->device_name, result)); - return result; -} - -/* - * set modem control signals (DTR/RTS) - * - * cmd signal command: TIOCMBIS = set bit TIOCMBIC = clear bit - * TIOCMSET = set/clear signal values - * value bit mask for command - */ -static int tiocmset(struct tty_struct *tty, - unsigned int set, unsigned int clear) -{ - struct slgt_info *info = tty->driver_data; - unsigned long flags; - - DBGINFO(("%s tiocmset(%x,%x)\n", info->device_name, set, clear)); - - if (set & TIOCM_RTS) - info->signals |= SerialSignal_RTS; - if (set & TIOCM_DTR) - info->signals |= SerialSignal_DTR; - if (clear & TIOCM_RTS) - info->signals &= ~SerialSignal_RTS; - if (clear & TIOCM_DTR) - info->signals &= ~SerialSignal_DTR; - - spin_lock_irqsave(&info->lock,flags); - set_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); - return 0; -} - -static bool carrier_raised(struct tty_port *port) -{ - unsigned long flags; - struct slgt_info *info = container_of(port, struct slgt_info, port); - - spin_lock_irqsave(&info->lock,flags); - get_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); - - return info->signals & SerialSignal_DCD; -} - -static void dtr_rts(struct tty_port *port, bool active) -{ - unsigned long flags; - struct slgt_info *info = container_of(port, struct slgt_info, port); - - spin_lock_irqsave(&info->lock,flags); - if (active) - info->signals |= SerialSignal_RTS | SerialSignal_DTR; - else - info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_gtsignals(info); - spin_unlock_irqrestore(&info->lock,flags); -} - - -/* - * block current process until the device is ready to open - */ -static int block_til_ready(struct tty_struct *tty, struct file *filp, - struct slgt_info *info) -{ - DECLARE_WAITQUEUE(wait, current); - int retval; - bool do_clocal = false; - unsigned long flags; - bool cd; - struct tty_port *port = &info->port; - - DBGINFO(("%s block_til_ready\n", tty->driver->name)); - - if (filp->f_flags & O_NONBLOCK || tty_io_error(tty)) { - /* nonblock mode is set or port is not enabled */ - tty_port_set_active(port, true); - return 0; - } - - if (C_CLOCAL(tty)) - do_clocal = true; - - /* Wait for carrier detect and the line to become - * free (i.e., not in use by the callout). While we are in - * this loop, port->count is dropped by one, so that - * close() knows when to free things. We restore it upon - * exit, either normal or abnormal. - */ - - retval = 0; - add_wait_queue(&port->open_wait, &wait); - - spin_lock_irqsave(&info->lock, flags); - port->count--; - spin_unlock_irqrestore(&info->lock, flags); - port->blocked_open++; - - while (1) { - if (C_BAUD(tty) && tty_port_initialized(port)) - tty_port_raise_dtr_rts(port); - - set_current_state(TASK_INTERRUPTIBLE); - - if (tty_hung_up_p(filp) || !tty_port_initialized(port)) { - retval = (port->flags & ASYNC_HUP_NOTIFY) ? - -EAGAIN : -ERESTARTSYS; - break; - } - - cd = tty_port_carrier_raised(port); - if (do_clocal || cd) - break; - - if (signal_pending(current)) { - retval = -ERESTARTSYS; - break; - } - - DBGINFO(("%s block_til_ready wait\n", tty->driver->name)); - tty_unlock(tty); - schedule(); - tty_lock(tty); - } - - set_current_state(TASK_RUNNING); - remove_wait_queue(&port->open_wait, &wait); - - if (!tty_hung_up_p(filp)) - port->count++; - port->blocked_open--; - - if (!retval) - tty_port_set_active(port, true); - - DBGINFO(("%s block_til_ready ready, rc=%d\n", tty->driver->name, retval)); - return retval; -} - -/* - * allocate buffers used for calling line discipline receive_buf - * directly in synchronous mode - * note: add 5 bytes to max frame size to allow appending - * 32-bit CRC and status byte when configured to do so - */ -static int alloc_tmp_rbuf(struct slgt_info *info) -{ - info->tmp_rbuf = kmalloc(info->max_frame_size + 5, GFP_KERNEL); - if (info->tmp_rbuf == NULL) - return -ENOMEM; - - return 0; -} - -static void free_tmp_rbuf(struct slgt_info *info) -{ - kfree(info->tmp_rbuf); - info->tmp_rbuf = NULL; -} - -/* - * allocate DMA descriptor lists. - */ -static int alloc_desc(struct slgt_info *info) -{ - unsigned int i; - unsigned int pbufs; - - /* allocate memory to hold descriptor lists */ - info->bufs = dma_alloc_coherent(&info->pdev->dev, DESC_LIST_SIZE, - &info->bufs_dma_addr, GFP_KERNEL); - if (info->bufs == NULL) - return -ENOMEM; - - info->rbufs = (struct slgt_desc*)info->bufs; - info->tbufs = ((struct slgt_desc*)info->bufs) + info->rbuf_count; - - pbufs = (unsigned int)info->bufs_dma_addr; - - /* - * Build circular lists of descriptors - */ - - for (i=0; i < info->rbuf_count; i++) { - /* physical address of this descriptor */ - info->rbufs[i].pdesc = pbufs + (i * sizeof(struct slgt_desc)); - - /* physical address of next descriptor */ - if (i == info->rbuf_count - 1) - info->rbufs[i].next = cpu_to_le32(pbufs); - else - info->rbufs[i].next = cpu_to_le32(pbufs + ((i+1) * sizeof(struct slgt_desc))); - set_desc_count(info->rbufs[i], DMABUFSIZE); - } - - for (i=0; i < info->tbuf_count; i++) { - /* physical address of this descriptor */ - info->tbufs[i].pdesc = pbufs + ((info->rbuf_count + i) * sizeof(struct slgt_desc)); - - /* physical address of next descriptor */ - if (i == info->tbuf_count - 1) - info->tbufs[i].next = cpu_to_le32(pbufs + info->rbuf_count * sizeof(struct slgt_desc)); - else - info->tbufs[i].next = cpu_to_le32(pbufs + ((info->rbuf_count + i + 1) * sizeof(struct slgt_desc))); - } - - return 0; -} - -static void free_desc(struct slgt_info *info) -{ - if (info->bufs != NULL) { - dma_free_coherent(&info->pdev->dev, DESC_LIST_SIZE, - info->bufs, info->bufs_dma_addr); - info->bufs = NULL; - info->rbufs = NULL; - info->tbufs = NULL; - } -} - -static int alloc_bufs(struct slgt_info *info, struct slgt_desc *bufs, int count) -{ - int i; - for (i=0; i < count; i++) { - bufs[i].buf = dma_alloc_coherent(&info->pdev->dev, DMABUFSIZE, - &bufs[i].buf_dma_addr, GFP_KERNEL); - if (!bufs[i].buf) - return -ENOMEM; - bufs[i].pbuf = cpu_to_le32((unsigned int)bufs[i].buf_dma_addr); - } - return 0; -} - -static void free_bufs(struct slgt_info *info, struct slgt_desc *bufs, int count) -{ - int i; - for (i=0; i < count; i++) { - if (bufs[i].buf == NULL) - continue; - dma_free_coherent(&info->pdev->dev, DMABUFSIZE, bufs[i].buf, - bufs[i].buf_dma_addr); - bufs[i].buf = NULL; - } -} - -static int alloc_dma_bufs(struct slgt_info *info) -{ - info->rbuf_count = 32; - info->tbuf_count = 32; - - if (alloc_desc(info) < 0 || - alloc_bufs(info, info->rbufs, info->rbuf_count) < 0 || - alloc_bufs(info, info->tbufs, info->tbuf_count) < 0 || - alloc_tmp_rbuf(info) < 0) { - DBGERR(("%s DMA buffer alloc fail\n", info->device_name)); - return -ENOMEM; - } - reset_rbufs(info); - return 0; -} - -static void free_dma_bufs(struct slgt_info *info) -{ - if (info->bufs) { - free_bufs(info, info->rbufs, info->rbuf_count); - free_bufs(info, info->tbufs, info->tbuf_count); - free_desc(info); - } - free_tmp_rbuf(info); -} - -static int claim_resources(struct slgt_info *info) -{ - if (request_mem_region(info->phys_reg_addr, SLGT_REG_SIZE, "synclink_gt") == NULL) { - DBGERR(("%s reg addr conflict, addr=%08X\n", - info->device_name, info->phys_reg_addr)); - info->init_error = DiagStatus_AddressConflict; - goto errout; - } - else - info->reg_addr_requested = true; - - info->reg_addr = ioremap(info->phys_reg_addr, SLGT_REG_SIZE); - if (!info->reg_addr) { - DBGERR(("%s can't map device registers, addr=%08X\n", - info->device_name, info->phys_reg_addr)); - info->init_error = DiagStatus_CantAssignPciResources; - goto errout; - } - return 0; - -errout: - release_resources(info); - return -ENODEV; -} - -static void release_resources(struct slgt_info *info) -{ - if (info->irq_requested) { - free_irq(info->irq_level, info); - info->irq_requested = false; - } - - if (info->reg_addr_requested) { - release_mem_region(info->phys_reg_addr, SLGT_REG_SIZE); - info->reg_addr_requested = false; - } - - if (info->reg_addr) { - iounmap(info->reg_addr); - info->reg_addr = NULL; - } -} - -/* Add the specified device instance data structure to the - * global linked list of devices and increment the device count. - */ -static void add_device(struct slgt_info *info) -{ - char *devstr; - - info->next_device = NULL; - info->line = slgt_device_count; - sprintf(info->device_name, "%s%d", tty_dev_prefix, info->line); - - if (info->line < MAX_DEVICES) { - if (maxframe[info->line]) - info->max_frame_size = maxframe[info->line]; - } - - slgt_device_count++; - - if (!slgt_device_list) - slgt_device_list = info; - else { - struct slgt_info *current_dev = slgt_device_list; - while(current_dev->next_device) - current_dev = current_dev->next_device; - current_dev->next_device = info; - } - - if (info->max_frame_size < 4096) - info->max_frame_size = 4096; - else if (info->max_frame_size > 65535) - info->max_frame_size = 65535; - - switch(info->pdev->device) { - case SYNCLINK_GT_DEVICE_ID: - devstr = "GT"; - break; - case SYNCLINK_GT2_DEVICE_ID: - devstr = "GT2"; - break; - case SYNCLINK_GT4_DEVICE_ID: - devstr = "GT4"; - break; - case SYNCLINK_AC_DEVICE_ID: - devstr = "AC"; - info->params.mode = MGSL_MODE_ASYNC; - break; - default: - devstr = "(unknown model)"; - } - printk("SyncLink %s %s IO=%08x IRQ=%d MaxFrameSize=%u\n", - devstr, info->device_name, info->phys_reg_addr, - info->irq_level, info->max_frame_size); - -#if SYNCLINK_GENERIC_HDLC - hdlcdev_init(info); -#endif -} - -static const struct tty_port_operations slgt_port_ops = { - .carrier_raised = carrier_raised, - .dtr_rts = dtr_rts, -}; - -/* - * allocate device instance structure, return NULL on failure - */ -static struct slgt_info *alloc_dev(int adapter_num, int port_num, struct pci_dev *pdev) -{ - struct slgt_info *info; - - info = kzalloc_obj(struct slgt_info); - - if (!info) { - DBGERR(("%s device alloc failed adapter=%d port=%d\n", - driver_name, adapter_num, port_num)); - } else { - tty_port_init(&info->port); - info->port.ops = &slgt_port_ops; - INIT_WORK(&info->task, bh_handler); - info->max_frame_size = 4096; - info->base_clock = 14745600; - info->rbuf_fill_level = DMABUFSIZE; - init_waitqueue_head(&info->status_event_wait_q); - init_waitqueue_head(&info->event_wait_q); - spin_lock_init(&info->netlock); - memcpy(&info->params,&default_params,sizeof(MGSL_PARAMS)); - info->idle_mode = HDLC_TXIDLE_FLAGS; - info->adapter_num = adapter_num; - info->port_num = port_num; - - timer_setup(&info->tx_timer, tx_timeout, 0); - timer_setup(&info->rx_timer, rx_timeout, 0); - - /* Copy configuration info to device instance data */ - info->pdev = pdev; - info->irq_level = pdev->irq; - info->phys_reg_addr = pci_resource_start(pdev,0); - - info->bus_type = MGSL_BUS_TYPE_PCI; - info->irq_flags = IRQF_SHARED; - - info->init_error = -1; /* assume error, set to 0 on successful init */ - } - - return info; -} - -static void device_init(int adapter_num, struct pci_dev *pdev) -{ - struct slgt_info *port_array[SLGT_MAX_PORTS]; - int i; - int port_count = 1; - - if (pdev->device == SYNCLINK_GT2_DEVICE_ID) - port_count = 2; - else if (pdev->device == SYNCLINK_GT4_DEVICE_ID) - port_count = 4; - - /* allocate device instances for all ports */ - for (i=0; i < port_count; ++i) { - port_array[i] = alloc_dev(adapter_num, i, pdev); - if (port_array[i] == NULL) { - for (--i; i >= 0; --i) { - tty_port_destroy(&port_array[i]->port); - kfree(port_array[i]); - } - return; - } - } - - /* give copy of port_array to all ports and add to device list */ - for (i=0; i < port_count; ++i) { - memcpy(port_array[i]->port_array, port_array, sizeof(port_array)); - add_device(port_array[i]); - port_array[i]->port_count = port_count; - spin_lock_init(&port_array[i]->lock); - } - - /* Allocate and claim adapter resources */ - if (!claim_resources(port_array[0])) { - - alloc_dma_bufs(port_array[0]); - - /* copy resource information from first port to others */ - for (i = 1; i < port_count; ++i) { - port_array[i]->irq_level = port_array[0]->irq_level; - port_array[i]->reg_addr = port_array[0]->reg_addr; - alloc_dma_bufs(port_array[i]); - } - - if (request_irq(port_array[0]->irq_level, - slgt_interrupt, - port_array[0]->irq_flags, - port_array[0]->device_name, - port_array[0]) < 0) { - DBGERR(("%s request_irq failed IRQ=%d\n", - port_array[0]->device_name, - port_array[0]->irq_level)); - } else { - port_array[0]->irq_requested = true; - adapter_test(port_array[0]); - for (i=1 ; i < port_count ; i++) { - port_array[i]->init_error = port_array[0]->init_error; - port_array[i]->gpio_present = port_array[0]->gpio_present; - } - } - } - - for (i = 0; i < port_count; ++i) { - struct slgt_info *info = port_array[i]; - tty_port_register_device(&info->port, serial_driver, info->line, - &info->pdev->dev); - } -} - -static int init_one(struct pci_dev *dev, - const struct pci_device_id *ent) -{ - if (pci_enable_device(dev)) { - printk("error enabling pci device %p\n", dev); - return -EIO; - } - pci_set_master(dev); - device_init(slgt_device_count, dev); - return 0; -} - -static void remove_one(struct pci_dev *dev) -{ -} - -static const struct tty_operations ops = { - .open = open, - .close = close, - .write = write, - .put_char = put_char, - .flush_chars = flush_chars, - .write_room = write_room, - .chars_in_buffer = chars_in_buffer, - .flush_buffer = flush_buffer, - .ioctl = ioctl, - .compat_ioctl = slgt_compat_ioctl, - .throttle = throttle, - .unthrottle = unthrottle, - .send_xchar = send_xchar, - .break_ctl = set_break, - .wait_until_sent = wait_until_sent, - .set_termios = set_termios, - .stop = tx_hold, - .start = tx_release, - .hangup = hangup, - .tiocmget = tiocmget, - .tiocmset = tiocmset, - .get_icount = get_icount, - .proc_show = synclink_gt_proc_show, -}; - -static void slgt_cleanup(void) -{ - struct slgt_info *info; - struct slgt_info *tmp; - - if (serial_driver) { - for (info=slgt_device_list ; info != NULL ; info=info->next_device) - tty_unregister_device(serial_driver, info->line); - tty_unregister_driver(serial_driver); - tty_driver_kref_put(serial_driver); - } - - /* reset devices */ - info = slgt_device_list; - while(info) { - reset_port(info); - info = info->next_device; - } - - /* release devices */ - info = slgt_device_list; - while(info) { -#if SYNCLINK_GENERIC_HDLC - hdlcdev_exit(info); -#endif - free_dma_bufs(info); - free_tmp_rbuf(info); - if (info->port_num == 0) - release_resources(info); - tmp = info; - info = info->next_device; - tty_port_destroy(&tmp->port); - kfree(tmp); - } - - if (pci_registered) - pci_unregister_driver(&pci_driver); -} - -/* - * Driver initialization entry point. - */ -static int __init slgt_init(void) -{ - int rc; - - serial_driver = tty_alloc_driver(MAX_DEVICES, TTY_DRIVER_REAL_RAW | - TTY_DRIVER_DYNAMIC_DEV); - if (IS_ERR(serial_driver)) { - printk("%s can't allocate tty driver\n", driver_name); - return PTR_ERR(serial_driver); - } - - /* Initialize the tty_driver structure */ - - serial_driver->driver_name = "synclink_gt"; - serial_driver->name = tty_dev_prefix; - serial_driver->major = ttymajor; - serial_driver->minor_start = 64; - serial_driver->type = TTY_DRIVER_TYPE_SERIAL; - serial_driver->subtype = SERIAL_TYPE_NORMAL; - serial_driver->init_termios = tty_std_termios; - serial_driver->init_termios.c_cflag = - B9600 | CS8 | CREAD | HUPCL | CLOCAL; - serial_driver->init_termios.c_ispeed = 9600; - serial_driver->init_termios.c_ospeed = 9600; - tty_set_operations(serial_driver, &ops); - if ((rc = tty_register_driver(serial_driver)) < 0) { - DBGERR(("%s can't register serial driver\n", driver_name)); - tty_driver_kref_put(serial_driver); - serial_driver = NULL; - goto error; - } - - slgt_device_count = 0; - if ((rc = pci_register_driver(&pci_driver)) < 0) { - printk("%s pci_register_driver error=%d\n", driver_name, rc); - goto error; - } - pci_registered = true; - - return 0; - -error: - slgt_cleanup(); - return rc; -} - -static void __exit slgt_exit(void) -{ - slgt_cleanup(); -} - -module_init(slgt_init); -module_exit(slgt_exit); - -/* - * register access routines - */ - -static inline void __iomem *calc_regaddr(struct slgt_info *info, - unsigned int addr) -{ - void __iomem *reg_addr = info->reg_addr + addr; - - if (addr >= 0x80) - reg_addr += info->port_num * 32; - else if (addr >= 0x40) - reg_addr += info->port_num * 16; - - return reg_addr; -} - -static __u8 rd_reg8(struct slgt_info *info, unsigned int addr) -{ - return readb(calc_regaddr(info, addr)); -} - -static void wr_reg8(struct slgt_info *info, unsigned int addr, __u8 value) -{ - writeb(value, calc_regaddr(info, addr)); -} - -static __u16 rd_reg16(struct slgt_info *info, unsigned int addr) -{ - return readw(calc_regaddr(info, addr)); -} - -static void wr_reg16(struct slgt_info *info, unsigned int addr, __u16 value) -{ - writew(value, calc_regaddr(info, addr)); -} - -static __u32 rd_reg32(struct slgt_info *info, unsigned int addr) -{ - return readl(calc_regaddr(info, addr)); -} - -static void wr_reg32(struct slgt_info *info, unsigned int addr, __u32 value) -{ - writel(value, calc_regaddr(info, addr)); -} - -static void rdma_reset(struct slgt_info *info) -{ - unsigned int i; - - /* set reset bit */ - wr_reg32(info, RDCSR, BIT1); - - /* wait for enable bit cleared */ - for(i=0 ; i < 1000 ; i++) - if (!(rd_reg32(info, RDCSR) & BIT0)) - break; -} - -static void tdma_reset(struct slgt_info *info) -{ - unsigned int i; - - /* set reset bit */ - wr_reg32(info, TDCSR, BIT1); - - /* wait for enable bit cleared */ - for(i=0 ; i < 1000 ; i++) - if (!(rd_reg32(info, TDCSR) & BIT0)) - break; -} - -/* - * enable internal loopback - * TxCLK and RxCLK are generated from BRG - * and TxD is looped back to RxD internally. - */ -static void enable_loopback(struct slgt_info *info) -{ - /* SCR (serial control) BIT2=loopback enable */ - wr_reg16(info, SCR, (unsigned short)(rd_reg16(info, SCR) | BIT2)); - - if (info->params.mode != MGSL_MODE_ASYNC) { - /* CCR (clock control) - * 07..05 tx clock source (010 = BRG) - * 04..02 rx clock source (010 = BRG) - * 01 auxclk enable (0 = disable) - * 00 BRG enable (1 = enable) - * - * 0100 1001 - */ - wr_reg8(info, CCR, 0x49); - - /* set speed if available, otherwise use default */ - if (info->params.clock_speed) - set_rate(info, info->params.clock_speed); - else - set_rate(info, 3686400); - } -} - -/* - * set baud rate generator to specified rate - */ -static void set_rate(struct slgt_info *info, u32 rate) -{ - unsigned int div; - unsigned int osc = info->base_clock; - - /* div = osc/rate - 1 - * - * Round div up if osc/rate is not integer to - * force to next slowest rate. - */ - - if (rate) { - div = osc/rate; - if (!(osc % rate) && div) - div--; - wr_reg16(info, BDR, (unsigned short)div); - } -} - -static void rx_stop(struct slgt_info *info) -{ - unsigned short val; - - /* disable and reset receiver */ - val = rd_reg16(info, RCR) & ~BIT1; /* clear enable bit */ - wr_reg16(info, RCR, (unsigned short)(val | BIT2)); /* set reset bit */ - wr_reg16(info, RCR, val); /* clear reset bit */ - - slgt_irq_off(info, IRQ_RXOVER + IRQ_RXDATA + IRQ_RXIDLE); - - /* clear pending rx interrupts */ - wr_reg16(info, SSR, IRQ_RXIDLE + IRQ_RXOVER); - - rdma_reset(info); - - info->rx_enabled = false; - info->rx_restart = false; -} - -static void rx_start(struct slgt_info *info) -{ - unsigned short val; - - slgt_irq_off(info, IRQ_RXOVER + IRQ_RXDATA); - - /* clear pending rx overrun IRQ */ - wr_reg16(info, SSR, IRQ_RXOVER); - - /* reset and disable receiver */ - val = rd_reg16(info, RCR) & ~BIT1; /* clear enable bit */ - wr_reg16(info, RCR, (unsigned short)(val | BIT2)); /* set reset bit */ - wr_reg16(info, RCR, val); /* clear reset bit */ - - rdma_reset(info); - reset_rbufs(info); - - if (info->rx_pio) { - /* rx request when rx FIFO not empty */ - wr_reg16(info, SCR, (unsigned short)(rd_reg16(info, SCR) & ~BIT14)); - slgt_irq_on(info, IRQ_RXDATA); - if (info->params.mode == MGSL_MODE_ASYNC) { - /* enable saving of rx status */ - wr_reg32(info, RDCSR, BIT6); - } - } else { - /* rx request when rx FIFO half full */ - wr_reg16(info, SCR, (unsigned short)(rd_reg16(info, SCR) | BIT14)); - /* set 1st descriptor address */ - wr_reg32(info, RDDAR, info->rbufs[0].pdesc); - - if (info->params.mode != MGSL_MODE_ASYNC) { - /* enable rx DMA and DMA interrupt */ - wr_reg32(info, RDCSR, (BIT2 + BIT0)); - } else { - /* enable saving of rx status, rx DMA and DMA interrupt */ - wr_reg32(info, RDCSR, (BIT6 + BIT2 + BIT0)); - } - } - - slgt_irq_on(info, IRQ_RXOVER); - - /* enable receiver */ - wr_reg16(info, RCR, (unsigned short)(rd_reg16(info, RCR) | BIT1)); - - info->rx_restart = false; - info->rx_enabled = true; -} - -static void tx_start(struct slgt_info *info) -{ - if (!info->tx_enabled) { - wr_reg16(info, TCR, - (unsigned short)((rd_reg16(info, TCR) | BIT1) & ~BIT2)); - info->tx_enabled = true; - } - - if (desc_count(info->tbufs[info->tbuf_start])) { - info->drop_rts_on_tx_done = false; - - if (info->params.mode != MGSL_MODE_ASYNC) { - if (info->params.flags & HDLC_FLAG_AUTO_RTS) { - get_gtsignals(info); - if (!(info->signals & SerialSignal_RTS)) { - info->signals |= SerialSignal_RTS; - set_gtsignals(info); - info->drop_rts_on_tx_done = true; - } - } - - slgt_irq_off(info, IRQ_TXDATA); - slgt_irq_on(info, IRQ_TXUNDER + IRQ_TXIDLE); - /* clear tx idle and underrun status bits */ - wr_reg16(info, SSR, (unsigned short)(IRQ_TXIDLE + IRQ_TXUNDER)); - } else { - slgt_irq_off(info, IRQ_TXDATA); - slgt_irq_on(info, IRQ_TXIDLE); - /* clear tx idle status bit */ - wr_reg16(info, SSR, IRQ_TXIDLE); - } - /* set 1st descriptor address and start DMA */ - wr_reg32(info, TDDAR, info->tbufs[info->tbuf_start].pdesc); - wr_reg32(info, TDCSR, BIT2 + BIT0); - info->tx_active = true; - } -} - -static void tx_stop(struct slgt_info *info) -{ - unsigned short val; - - timer_delete(&info->tx_timer); - - tdma_reset(info); - - /* reset and disable transmitter */ - val = rd_reg16(info, TCR) & ~BIT1; /* clear enable bit */ - wr_reg16(info, TCR, (unsigned short)(val | BIT2)); /* set reset bit */ - - slgt_irq_off(info, IRQ_TXDATA + IRQ_TXIDLE + IRQ_TXUNDER); - - /* clear tx idle and underrun status bit */ - wr_reg16(info, SSR, (unsigned short)(IRQ_TXIDLE + IRQ_TXUNDER)); - - reset_tbufs(info); - - info->tx_enabled = false; - info->tx_active = false; -} - -static void reset_port(struct slgt_info *info) -{ - if (!info->reg_addr) - return; - - tx_stop(info); - rx_stop(info); - - info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_gtsignals(info); - - slgt_irq_off(info, IRQ_ALL | IRQ_MASTER); -} - -static void reset_adapter(struct slgt_info *info) -{ - int i; - for (i=0; i < info->port_count; ++i) { - if (info->port_array[i]) - reset_port(info->port_array[i]); - } -} - -static void async_mode(struct slgt_info *info) -{ - unsigned short val; - - slgt_irq_off(info, IRQ_ALL | IRQ_MASTER); - tx_stop(info); - rx_stop(info); - - /* TCR (tx control) - * - * 15..13 mode, 010=async - * 12..10 encoding, 000=NRZ - * 09 parity enable - * 08 1=odd parity, 0=even parity - * 07 1=RTS driver control - * 06 1=break enable - * 05..04 character length - * 00=5 bits - * 01=6 bits - * 10=7 bits - * 11=8 bits - * 03 0=1 stop bit, 1=2 stop bits - * 02 reset - * 01 enable - * 00 auto-CTS enable - */ - val = 0x4000; - - if (info->if_mode & MGSL_INTERFACE_RTS_EN) - val |= BIT7; - - if (info->params.parity != ASYNC_PARITY_NONE) { - val |= BIT9; - if (info->params.parity == ASYNC_PARITY_ODD) - val |= BIT8; - } - - switch (info->params.data_bits) - { - case 6: val |= BIT4; break; - case 7: val |= BIT5; break; - case 8: val |= BIT5 + BIT4; break; - } - - if (info->params.stop_bits != 1) - val |= BIT3; - - if (info->params.flags & HDLC_FLAG_AUTO_CTS) - val |= BIT0; - - wr_reg16(info, TCR, val); - - /* RCR (rx control) - * - * 15..13 mode, 010=async - * 12..10 encoding, 000=NRZ - * 09 parity enable - * 08 1=odd parity, 0=even parity - * 07..06 reserved, must be 0 - * 05..04 character length - * 00=5 bits - * 01=6 bits - * 10=7 bits - * 11=8 bits - * 03 reserved, must be zero - * 02 reset - * 01 enable - * 00 auto-DCD enable - */ - val = 0x4000; - - if (info->params.parity != ASYNC_PARITY_NONE) { - val |= BIT9; - if (info->params.parity == ASYNC_PARITY_ODD) - val |= BIT8; - } - - switch (info->params.data_bits) - { - case 6: val |= BIT4; break; - case 7: val |= BIT5; break; - case 8: val |= BIT5 + BIT4; break; - } - - if (info->params.flags & HDLC_FLAG_AUTO_DCD) - val |= BIT0; - - wr_reg16(info, RCR, val); - - /* CCR (clock control) - * - * 07..05 011 = tx clock source is BRG/16 - * 04..02 010 = rx clock source is BRG - * 01 0 = auxclk disabled - * 00 1 = BRG enabled - * - * 0110 1001 - */ - wr_reg8(info, CCR, 0x69); - - msc_set_vcr(info); - - /* SCR (serial control) - * - * 15 1=tx req on FIFO half empty - * 14 1=rx req on FIFO half full - * 13 tx data IRQ enable - * 12 tx idle IRQ enable - * 11 rx break on IRQ enable - * 10 rx data IRQ enable - * 09 rx break off IRQ enable - * 08 overrun IRQ enable - * 07 DSR IRQ enable - * 06 CTS IRQ enable - * 05 DCD IRQ enable - * 04 RI IRQ enable - * 03 0=16x sampling, 1=8x sampling - * 02 1=txd->rxd internal loopback enable - * 01 reserved, must be zero - * 00 1=master IRQ enable - */ - val = BIT15 + BIT14 + BIT0; - /* JCR[8] : 1 = x8 async mode feature available */ - if ((rd_reg32(info, JCR) & BIT8) && info->params.data_rate && - ((info->base_clock < (info->params.data_rate * 16)) || - (info->base_clock % (info->params.data_rate * 16)))) { - /* use 8x sampling */ - val |= BIT3; - set_rate(info, info->params.data_rate * 8); - } else { - /* use 16x sampling */ - set_rate(info, info->params.data_rate * 16); - } - wr_reg16(info, SCR, val); - - slgt_irq_on(info, IRQ_RXBREAK | IRQ_RXOVER); - - if (info->params.loopback) - enable_loopback(info); -} - -static void sync_mode(struct slgt_info *info) -{ - unsigned short val; - - slgt_irq_off(info, IRQ_ALL | IRQ_MASTER); - tx_stop(info); - rx_stop(info); - - /* TCR (tx control) - * - * 15..13 mode - * 000=HDLC/SDLC - * 001=raw bit synchronous - * 010=asynchronous/isochronous - * 011=monosync byte synchronous - * 100=bisync byte synchronous - * 101=xsync byte synchronous - * 12..10 encoding - * 09 CRC enable - * 08 CRC32 - * 07 1=RTS driver control - * 06 preamble enable - * 05..04 preamble length - * 03 share open/close flag - * 02 reset - * 01 enable - * 00 auto-CTS enable - */ - val = BIT2; - - switch(info->params.mode) { - case MGSL_MODE_XSYNC: - val |= BIT15 + BIT13; - break; - case MGSL_MODE_MONOSYNC: val |= BIT14 + BIT13; break; - case MGSL_MODE_BISYNC: val |= BIT15; break; - case MGSL_MODE_RAW: val |= BIT13; break; - } - if (info->if_mode & MGSL_INTERFACE_RTS_EN) - val |= BIT7; - - switch(info->params.encoding) - { - case HDLC_ENCODING_NRZB: val |= BIT10; break; - case HDLC_ENCODING_NRZI_MARK: val |= BIT11; break; - case HDLC_ENCODING_NRZI: val |= BIT11 + BIT10; break; - case HDLC_ENCODING_BIPHASE_MARK: val |= BIT12; break; - case HDLC_ENCODING_BIPHASE_SPACE: val |= BIT12 + BIT10; break; - case HDLC_ENCODING_BIPHASE_LEVEL: val |= BIT12 + BIT11; break; - case HDLC_ENCODING_DIFF_BIPHASE_LEVEL: val |= BIT12 + BIT11 + BIT10; break; - } - - switch (info->params.crc_type & HDLC_CRC_MASK) - { - case HDLC_CRC_16_CCITT: val |= BIT9; break; - case HDLC_CRC_32_CCITT: val |= BIT9 + BIT8; break; - } - - if (info->params.preamble != HDLC_PREAMBLE_PATTERN_NONE) - val |= BIT6; - - switch (info->params.preamble_length) - { - case HDLC_PREAMBLE_LENGTH_16BITS: val |= BIT5; break; - case HDLC_PREAMBLE_LENGTH_32BITS: val |= BIT4; break; - case HDLC_PREAMBLE_LENGTH_64BITS: val |= BIT5 + BIT4; break; - } - - if (info->params.flags & HDLC_FLAG_AUTO_CTS) - val |= BIT0; - - wr_reg16(info, TCR, val); - - /* TPR (transmit preamble) */ - - switch (info->params.preamble) - { - case HDLC_PREAMBLE_PATTERN_FLAGS: val = 0x7e; break; - case HDLC_PREAMBLE_PATTERN_ONES: val = 0xff; break; - case HDLC_PREAMBLE_PATTERN_ZEROS: val = 0x00; break; - case HDLC_PREAMBLE_PATTERN_10: val = 0x55; break; - case HDLC_PREAMBLE_PATTERN_01: val = 0xaa; break; - default: val = 0x7e; break; - } - wr_reg8(info, TPR, (unsigned char)val); - - /* RCR (rx control) - * - * 15..13 mode - * 000=HDLC/SDLC - * 001=raw bit synchronous - * 010=asynchronous/isochronous - * 011=monosync byte synchronous - * 100=bisync byte synchronous - * 101=xsync byte synchronous - * 12..10 encoding - * 09 CRC enable - * 08 CRC32 - * 07..03 reserved, must be 0 - * 02 reset - * 01 enable - * 00 auto-DCD enable - */ - val = 0; - - switch(info->params.mode) { - case MGSL_MODE_XSYNC: - val |= BIT15 + BIT13; - break; - case MGSL_MODE_MONOSYNC: val |= BIT14 + BIT13; break; - case MGSL_MODE_BISYNC: val |= BIT15; break; - case MGSL_MODE_RAW: val |= BIT13; break; - } - - switch(info->params.encoding) - { - case HDLC_ENCODING_NRZB: val |= BIT10; break; - case HDLC_ENCODING_NRZI_MARK: val |= BIT11; break; - case HDLC_ENCODING_NRZI: val |= BIT11 + BIT10; break; - case HDLC_ENCODING_BIPHASE_MARK: val |= BIT12; break; - case HDLC_ENCODING_BIPHASE_SPACE: val |= BIT12 + BIT10; break; - case HDLC_ENCODING_BIPHASE_LEVEL: val |= BIT12 + BIT11; break; - case HDLC_ENCODING_DIFF_BIPHASE_LEVEL: val |= BIT12 + BIT11 + BIT10; break; - } - - switch (info->params.crc_type & HDLC_CRC_MASK) - { - case HDLC_CRC_16_CCITT: val |= BIT9; break; - case HDLC_CRC_32_CCITT: val |= BIT9 + BIT8; break; - } - - if (info->params.flags & HDLC_FLAG_AUTO_DCD) - val |= BIT0; - - wr_reg16(info, RCR, val); - - /* CCR (clock control) - * - * 07..05 tx clock source - * 04..02 rx clock source - * 01 auxclk enable - * 00 BRG enable - */ - val = 0; - - if (info->params.flags & HDLC_FLAG_TXC_BRG) - { - // when RxC source is DPLL, BRG generates 16X DPLL - // reference clock, so take TxC from BRG/16 to get - // transmit clock at actual data rate - if (info->params.flags & HDLC_FLAG_RXC_DPLL) - val |= BIT6 + BIT5; /* 011, txclk = BRG/16 */ - else - val |= BIT6; /* 010, txclk = BRG */ - } - else if (info->params.flags & HDLC_FLAG_TXC_DPLL) - val |= BIT7; /* 100, txclk = DPLL Input */ - else if (info->params.flags & HDLC_FLAG_TXC_RXCPIN) - val |= BIT5; /* 001, txclk = RXC Input */ - - if (info->params.flags & HDLC_FLAG_RXC_BRG) - val |= BIT3; /* 010, rxclk = BRG */ - else if (info->params.flags & HDLC_FLAG_RXC_DPLL) - val |= BIT4; /* 100, rxclk = DPLL */ - else if (info->params.flags & HDLC_FLAG_RXC_TXCPIN) - val |= BIT2; /* 001, rxclk = TXC Input */ - - if (info->params.clock_speed) - val |= BIT1 + BIT0; - - wr_reg8(info, CCR, (unsigned char)val); - - if (info->params.flags & (HDLC_FLAG_TXC_DPLL + HDLC_FLAG_RXC_DPLL)) - { - // program DPLL mode - switch(info->params.encoding) - { - case HDLC_ENCODING_BIPHASE_MARK: - case HDLC_ENCODING_BIPHASE_SPACE: - val = BIT7; break; - case HDLC_ENCODING_BIPHASE_LEVEL: - case HDLC_ENCODING_DIFF_BIPHASE_LEVEL: - val = BIT7 + BIT6; break; - default: val = BIT6; // NRZ encodings - } - wr_reg16(info, RCR, (unsigned short)(rd_reg16(info, RCR) | val)); - - // DPLL requires a 16X reference clock from BRG - set_rate(info, info->params.clock_speed * 16); - } - else - set_rate(info, info->params.clock_speed); - - tx_set_idle(info); - - msc_set_vcr(info); - - /* SCR (serial control) - * - * 15 1=tx req on FIFO half empty - * 14 1=rx req on FIFO half full - * 13 tx data IRQ enable - * 12 tx idle IRQ enable - * 11 underrun IRQ enable - * 10 rx data IRQ enable - * 09 rx idle IRQ enable - * 08 overrun IRQ enable - * 07 DSR IRQ enable - * 06 CTS IRQ enable - * 05 DCD IRQ enable - * 04 RI IRQ enable - * 03 reserved, must be zero - * 02 1=txd->rxd internal loopback enable - * 01 reserved, must be zero - * 00 1=master IRQ enable - */ - wr_reg16(info, SCR, BIT15 + BIT14 + BIT0); - - if (info->params.loopback) - enable_loopback(info); -} - -/* - * set transmit idle mode - */ -static void tx_set_idle(struct slgt_info *info) -{ - unsigned char val; - unsigned short tcr; - - /* if preamble enabled (tcr[6] == 1) then tx idle size = 8 bits - * else tcr[5:4] = tx idle size: 00 = 8 bits, 01 = 16 bits - */ - tcr = rd_reg16(info, TCR); - if (info->idle_mode & HDLC_TXIDLE_CUSTOM_16) { - /* disable preamble, set idle size to 16 bits */ - tcr = (tcr & ~(BIT6 + BIT5)) | BIT4; - /* MSB of 16 bit idle specified in tx preamble register (TPR) */ - wr_reg8(info, TPR, (unsigned char)((info->idle_mode >> 8) & 0xff)); - } else if (!(tcr & BIT6)) { - /* preamble is disabled, set idle size to 8 bits */ - tcr &= ~(BIT5 + BIT4); - } - wr_reg16(info, TCR, tcr); - - if (info->idle_mode & (HDLC_TXIDLE_CUSTOM_8 | HDLC_TXIDLE_CUSTOM_16)) { - /* LSB of custom tx idle specified in tx idle register */ - val = (unsigned char)(info->idle_mode & 0xff); - } else { - /* standard 8 bit idle patterns */ - switch(info->idle_mode) - { - case HDLC_TXIDLE_FLAGS: val = 0x7e; break; - case HDLC_TXIDLE_ALT_ZEROS_ONES: - case HDLC_TXIDLE_ALT_MARK_SPACE: val = 0xaa; break; - case HDLC_TXIDLE_ZEROS: - case HDLC_TXIDLE_SPACE: val = 0x00; break; - default: val = 0xff; - } - } - - wr_reg8(info, TIR, val); -} - -/* - * get state of V24 status (input) signals - */ -static void get_gtsignals(struct slgt_info *info) -{ - unsigned short status = rd_reg16(info, SSR); - - /* clear all serial signals except RTS and DTR */ - info->signals &= SerialSignal_RTS | SerialSignal_DTR; - - if (status & BIT3) - info->signals |= SerialSignal_DSR; - if (status & BIT2) - info->signals |= SerialSignal_CTS; - if (status & BIT1) - info->signals |= SerialSignal_DCD; - if (status & BIT0) - info->signals |= SerialSignal_RI; -} - -/* - * set V.24 Control Register based on current configuration - */ -static void msc_set_vcr(struct slgt_info *info) -{ - unsigned char val = 0; - - /* VCR (V.24 control) - * - * 07..04 serial IF select - * 03 DTR - * 02 RTS - * 01 LL - * 00 RL - */ - - switch(info->if_mode & MGSL_INTERFACE_MASK) - { - case MGSL_INTERFACE_RS232: - val |= BIT5; /* 0010 */ - break; - case MGSL_INTERFACE_V35: - val |= BIT7 + BIT6 + BIT5; /* 1110 */ - break; - case MGSL_INTERFACE_RS422: - val |= BIT6; /* 0100 */ - break; - } - - if (info->if_mode & MGSL_INTERFACE_MSB_FIRST) - val |= BIT4; - if (info->signals & SerialSignal_DTR) - val |= BIT3; - if (info->signals & SerialSignal_RTS) - val |= BIT2; - if (info->if_mode & MGSL_INTERFACE_LL) - val |= BIT1; - if (info->if_mode & MGSL_INTERFACE_RL) - val |= BIT0; - wr_reg8(info, VCR, val); -} - -/* - * set state of V24 control (output) signals - */ -static void set_gtsignals(struct slgt_info *info) -{ - unsigned char val = rd_reg8(info, VCR); - if (info->signals & SerialSignal_DTR) - val |= BIT3; - else - val &= ~BIT3; - if (info->signals & SerialSignal_RTS) - val |= BIT2; - else - val &= ~BIT2; - wr_reg8(info, VCR, val); -} - -/* - * free range of receive DMA buffers (i to last) - */ -static void free_rbufs(struct slgt_info *info, unsigned int i, unsigned int last) -{ - int done = 0; - - while(!done) { - /* reset current buffer for reuse */ - info->rbufs[i].status = 0; - set_desc_count(info->rbufs[i], info->rbuf_fill_level); - if (i == last) - done = 1; - if (++i == info->rbuf_count) - i = 0; - } - info->rbuf_current = i; -} - -/* - * mark all receive DMA buffers as free - */ -static void reset_rbufs(struct slgt_info *info) -{ - free_rbufs(info, 0, info->rbuf_count - 1); - info->rbuf_fill_index = 0; - info->rbuf_fill_count = 0; -} - -/* - * pass receive HDLC frame to upper layer - * - * return true if frame available, otherwise false - */ -static bool rx_get_frame(struct slgt_info *info) -{ - unsigned int start, end; - unsigned short status; - unsigned int framesize = 0; - unsigned long flags; - struct tty_struct *tty = info->port.tty; - unsigned char addr_field = 0xff; - unsigned int crc_size = 0; - - switch (info->params.crc_type & HDLC_CRC_MASK) { - case HDLC_CRC_16_CCITT: crc_size = 2; break; - case HDLC_CRC_32_CCITT: crc_size = 4; break; - } - -check_again: - - framesize = 0; - addr_field = 0xff; - start = end = info->rbuf_current; - - for (;;) { - if (!desc_complete(info->rbufs[end])) - goto cleanup; - - if (framesize == 0 && info->params.addr_filter != 0xff) - addr_field = info->rbufs[end].buf[0]; - - framesize += desc_count(info->rbufs[end]); - - if (desc_eof(info->rbufs[end])) - break; - - if (++end == info->rbuf_count) - end = 0; - - if (end == info->rbuf_current) { - if (info->rx_enabled){ - spin_lock_irqsave(&info->lock,flags); - rx_start(info); - spin_unlock_irqrestore(&info->lock,flags); - } - goto cleanup; - } - } - - /* status - * - * 15 buffer complete - * 14..06 reserved - * 05..04 residue - * 02 eof (end of frame) - * 01 CRC error - * 00 abort - */ - status = desc_status(info->rbufs[end]); - - /* ignore CRC bit if not using CRC (bit is undefined) */ - if ((info->params.crc_type & HDLC_CRC_MASK) == HDLC_CRC_NONE) - status &= ~BIT1; - - if (framesize == 0 || - (addr_field != 0xff && addr_field != info->params.addr_filter)) { - free_rbufs(info, start, end); - goto check_again; - } - - if (framesize < (2 + crc_size) || status & BIT0) { - info->icount.rxshort++; - framesize = 0; - } else if (status & BIT1) { - info->icount.rxcrc++; - if (!(info->params.crc_type & HDLC_CRC_RETURN_EX)) - framesize = 0; - } - -#if SYNCLINK_GENERIC_HDLC - if (framesize == 0) { - info->netdev->stats.rx_errors++; - info->netdev->stats.rx_frame_errors++; - } -#endif - - DBGBH(("%s rx frame status=%04X size=%d\n", - info->device_name, status, framesize)); - DBGDATA(info, info->rbufs[start].buf, min_t(int, framesize, info->rbuf_fill_level), "rx"); - - if (framesize) { - if (!(info->params.crc_type & HDLC_CRC_RETURN_EX)) { - framesize -= crc_size; - crc_size = 0; - } - - if (framesize > info->max_frame_size + crc_size) - info->icount.rxlong++; - else { - /* copy dma buffer(s) to contiguous temp buffer */ - int copy_count = framesize; - int i = start; - unsigned char *p = info->tmp_rbuf; - info->tmp_rbuf_count = framesize; - - info->icount.rxok++; - - while(copy_count) { - int partial_count = min_t(int, copy_count, info->rbuf_fill_level); - memcpy(p, info->rbufs[i].buf, partial_count); - p += partial_count; - copy_count -= partial_count; - if (++i == info->rbuf_count) - i = 0; - } - - if (info->params.crc_type & HDLC_CRC_RETURN_EX) { - *p = (status & BIT1) ? RX_CRC_ERROR : RX_OK; - framesize++; - } - -#if SYNCLINK_GENERIC_HDLC - if (info->netcount) - hdlcdev_rx(info,info->tmp_rbuf, framesize); - else -#endif - ldisc_receive_buf(tty, info->tmp_rbuf, NULL, - framesize); - } - } - free_rbufs(info, start, end); - return true; - -cleanup: - return false; -} - -/* - * pass receive buffer (RAW synchronous mode) to tty layer - * return true if buffer available, otherwise false - */ -static bool rx_get_buf(struct slgt_info *info) -{ - unsigned int i = info->rbuf_current; - unsigned int count; - - if (!desc_complete(info->rbufs[i])) - return false; - count = desc_count(info->rbufs[i]); - switch(info->params.mode) { - case MGSL_MODE_MONOSYNC: - case MGSL_MODE_BISYNC: - case MGSL_MODE_XSYNC: - /* ignore residue in byte synchronous modes */ - if (desc_residue(info->rbufs[i])) - count--; - break; - } - DBGDATA(info, info->rbufs[i].buf, count, "rx"); - DBGINFO(("rx_get_buf size=%d\n", count)); - if (count) - ldisc_receive_buf(info->port.tty, info->rbufs[i].buf, NULL, - count); - free_rbufs(info, i, i); - return true; -} - -static void reset_tbufs(struct slgt_info *info) -{ - unsigned int i; - info->tbuf_current = 0; - for (i=0 ; i < info->tbuf_count ; i++) { - info->tbufs[i].status = 0; - info->tbufs[i].count = 0; - } -} - -/* - * return number of free transmit DMA buffers - */ -static unsigned int free_tbuf_count(struct slgt_info *info) -{ - unsigned int count = 0; - unsigned int i = info->tbuf_current; - - do - { - if (desc_count(info->tbufs[i])) - break; /* buffer in use */ - ++count; - if (++i == info->tbuf_count) - i=0; - } while (i != info->tbuf_current); - - /* if tx DMA active, last zero count buffer is in use */ - if (count && (rd_reg32(info, TDCSR) & BIT0)) - --count; - - return count; -} - -/* - * return number of bytes in unsent transmit DMA buffers - * and the serial controller tx FIFO - */ -static unsigned int tbuf_bytes(struct slgt_info *info) -{ - unsigned int total_count = 0; - unsigned int i = info->tbuf_current; - unsigned int reg_value; - unsigned int count; - unsigned int active_buf_count = 0; - - /* - * Add descriptor counts for all tx DMA buffers. - * If count is zero (cleared by DMA controller after read), - * the buffer is complete or is actively being read from. - * - * Record buf_count of last buffer with zero count starting - * from current ring position. buf_count is mirror - * copy of count and is not cleared by serial controller. - * If DMA controller is active, that buffer is actively - * being read so add to total. - */ - do { - count = desc_count(info->tbufs[i]); - if (count) - total_count += count; - else if (!total_count) - active_buf_count = info->tbufs[i].buf_count; - if (++i == info->tbuf_count) - i = 0; - } while (i != info->tbuf_current); - - /* read tx DMA status register */ - reg_value = rd_reg32(info, TDCSR); - - /* if tx DMA active, last zero count buffer is in use */ - if (reg_value & BIT0) - total_count += active_buf_count; - - /* add tx FIFO count = reg_value[15..8] */ - total_count += (reg_value >> 8) & 0xff; - - /* if transmitter active add one byte for shift register */ - if (info->tx_active) - total_count++; - - return total_count; -} - -/* - * load data into transmit DMA buffer ring and start transmitter if needed - * return true if data accepted, otherwise false (buffers full) - */ -static bool tx_load(struct slgt_info *info, const u8 *buf, unsigned int size) -{ - unsigned short count; - unsigned int i; - struct slgt_desc *d; - - /* check required buffer space */ - if (DIV_ROUND_UP(size, DMABUFSIZE) > free_tbuf_count(info)) - return false; - - DBGDATA(info, buf, size, "tx"); - - /* - * copy data to one or more DMA buffers in circular ring - * tbuf_start = first buffer for this data - * tbuf_current = next free buffer - * - * Copy all data before making data visible to DMA controller by - * setting descriptor count of the first buffer. - * This prevents an active DMA controller from reading the first DMA - * buffers of a frame and stopping before the final buffers are filled. - */ - - info->tbuf_start = i = info->tbuf_current; - - while (size) { - d = &info->tbufs[i]; - - count = (unsigned short)((size > DMABUFSIZE) ? DMABUFSIZE : size); - memcpy(d->buf, buf, count); - - size -= count; - buf += count; - - /* - * set EOF bit for last buffer of HDLC frame or - * for every buffer in raw mode - */ - if ((!size && info->params.mode == MGSL_MODE_HDLC) || - info->params.mode == MGSL_MODE_RAW) - set_desc_eof(*d, 1); - else - set_desc_eof(*d, 0); - - /* set descriptor count for all but first buffer */ - if (i != info->tbuf_start) - set_desc_count(*d, count); - d->buf_count = count; - - if (++i == info->tbuf_count) - i = 0; - } - - info->tbuf_current = i; - - /* set first buffer count to make new data visible to DMA controller */ - d = &info->tbufs[info->tbuf_start]; - set_desc_count(*d, d->buf_count); - - /* start transmitter if needed and update transmit timeout */ - if (!info->tx_active) - tx_start(info); - update_tx_timer(info); - - return true; -} - -static int register_test(struct slgt_info *info) -{ - static unsigned short patterns[] = - {0x0000, 0xffff, 0xaaaa, 0x5555, 0x6969, 0x9696}; - static unsigned int count = ARRAY_SIZE(patterns); - unsigned int i; - int rc = 0; - - for (i=0 ; i < count ; i++) { - wr_reg16(info, TIR, patterns[i]); - wr_reg16(info, BDR, patterns[(i+1)%count]); - if ((rd_reg16(info, TIR) != patterns[i]) || - (rd_reg16(info, BDR) != patterns[(i+1)%count])) { - rc = -ENODEV; - break; - } - } - info->gpio_present = (rd_reg32(info, JCR) & BIT5) ? 1 : 0; - info->init_error = rc ? 0 : DiagStatus_AddressFailure; - return rc; -} - -static int irq_test(struct slgt_info *info) -{ - unsigned long timeout; - unsigned long flags; - struct tty_struct *oldtty = info->port.tty; - u32 speed = info->params.data_rate; - - info->params.data_rate = 921600; - info->port.tty = NULL; - - spin_lock_irqsave(&info->lock, flags); - async_mode(info); - slgt_irq_on(info, IRQ_TXIDLE); - - /* enable transmitter */ - wr_reg16(info, TCR, - (unsigned short)(rd_reg16(info, TCR) | BIT1)); - - /* write one byte and wait for tx idle */ - wr_reg16(info, TDR, 0); - - /* assume failure */ - info->init_error = DiagStatus_IrqFailure; - info->irq_occurred = false; - - spin_unlock_irqrestore(&info->lock, flags); - - timeout=100; - while(timeout-- && !info->irq_occurred) - msleep_interruptible(10); - - spin_lock_irqsave(&info->lock,flags); - reset_port(info); - spin_unlock_irqrestore(&info->lock,flags); - - info->params.data_rate = speed; - info->port.tty = oldtty; - - info->init_error = info->irq_occurred ? 0 : DiagStatus_IrqFailure; - return info->irq_occurred ? 0 : -ENODEV; -} - -static int loopback_test_rx(struct slgt_info *info) -{ - unsigned char *src, *dest; - int count; - - if (desc_complete(info->rbufs[0])) { - count = desc_count(info->rbufs[0]); - src = info->rbufs[0].buf; - dest = info->tmp_rbuf; - - for( ; count ; count-=2, src+=2) { - /* src=data byte (src+1)=status byte */ - if (!(*(src+1) & (BIT9 + BIT8))) { - *dest = *src; - dest++; - info->tmp_rbuf_count++; - } - } - DBGDATA(info, info->tmp_rbuf, info->tmp_rbuf_count, "rx"); - return 1; - } - return 0; -} - -static int loopback_test(struct slgt_info *info) -{ -#define TESTFRAMESIZE 20 - - unsigned long timeout; - u16 count; - unsigned char buf[TESTFRAMESIZE]; - int rc = -ENODEV; - unsigned long flags; - - struct tty_struct *oldtty = info->port.tty; - MGSL_PARAMS params; - - memcpy(¶ms, &info->params, sizeof(params)); - - info->params.mode = MGSL_MODE_ASYNC; - info->params.data_rate = 921600; - info->params.loopback = 1; - info->port.tty = NULL; - - /* build and send transmit frame */ - for (count = 0; count < TESTFRAMESIZE; ++count) - buf[count] = (unsigned char)count; - - info->tmp_rbuf_count = 0; - memset(info->tmp_rbuf, 0, TESTFRAMESIZE); - - /* program hardware for HDLC and enabled receiver */ - spin_lock_irqsave(&info->lock,flags); - async_mode(info); - rx_start(info); - tx_load(info, buf, count); - spin_unlock_irqrestore(&info->lock, flags); - - /* wait for receive complete */ - for (timeout = 100; timeout; --timeout) { - msleep_interruptible(10); - if (loopback_test_rx(info)) { - rc = 0; - break; - } - } - - /* verify received frame length and contents */ - if (!rc && (info->tmp_rbuf_count != count || - memcmp(buf, info->tmp_rbuf, count))) { - rc = -ENODEV; - } - - spin_lock_irqsave(&info->lock,flags); - reset_adapter(info); - spin_unlock_irqrestore(&info->lock,flags); - - memcpy(&info->params, ¶ms, sizeof(info->params)); - info->port.tty = oldtty; - - info->init_error = rc ? DiagStatus_DmaFailure : 0; - return rc; -} - -static int adapter_test(struct slgt_info *info) -{ - DBGINFO(("testing %s\n", info->device_name)); - if (register_test(info) < 0) { - printk("register test failure %s addr=%08X\n", - info->device_name, info->phys_reg_addr); - } else if (irq_test(info) < 0) { - printk("IRQ test failure %s IRQ=%d\n", - info->device_name, info->irq_level); - } else if (loopback_test(info) < 0) { - printk("loopback test failure %s\n", info->device_name); - } - return info->init_error; -} - -/* - * transmit timeout handler - */ -static void tx_timeout(struct timer_list *t) -{ - struct slgt_info *info = timer_container_of(info, t, tx_timer); - unsigned long flags; - - DBGINFO(("%s tx_timeout\n", info->device_name)); - if(info->tx_active && info->params.mode == MGSL_MODE_HDLC) { - info->icount.txtimeout++; - } - spin_lock_irqsave(&info->lock,flags); - tx_stop(info); - spin_unlock_irqrestore(&info->lock,flags); - -#if SYNCLINK_GENERIC_HDLC - if (info->netcount) - hdlcdev_tx_done(info); - else -#endif - bh_transmit(info); -} - -/* - * receive buffer polling timer - */ -static void rx_timeout(struct timer_list *t) -{ - struct slgt_info *info = timer_container_of(info, t, rx_timer); - unsigned long flags; - - DBGINFO(("%s rx_timeout\n", info->device_name)); - spin_lock_irqsave(&info->lock, flags); - info->pending_bh |= BH_RECEIVE; - spin_unlock_irqrestore(&info->lock, flags); - bh_handler(&info->task); -} - diff --git a/include/linux/synclink.h b/include/linux/synclink.h deleted file mode 100644 index f1405b1c71ba..000000000000 --- a/include/linux/synclink.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * SyncLink Multiprotocol Serial Adapter Driver - * - * $Id: synclink.h,v 3.14 2006/07/17 20:15:43 paulkf Exp $ - * - * Copyright (C) 1998-2000 by Microgate Corporation - * - * Redistribution of this file is permitted under - * the terms of the GNU Public License (GPL) - */ -#ifndef _SYNCLINK_H_ -#define _SYNCLINK_H_ - -#include - -/* provide 32 bit ioctl compatibility on 64 bit systems */ -#ifdef CONFIG_COMPAT -#include -struct MGSL_PARAMS32 { - compat_ulong_t mode; - unsigned char loopback; - unsigned short flags; - unsigned char encoding; - compat_ulong_t clock_speed; - unsigned char addr_filter; - unsigned short crc_type; - unsigned char preamble_length; - unsigned char preamble; - compat_ulong_t data_rate; - unsigned char data_bits; - unsigned char stop_bits; - unsigned char parity; -}; -#define MGSL_IOCSPARAMS32 _IOW(MGSL_MAGIC_IOC,0,struct MGSL_PARAMS32) -#define MGSL_IOCGPARAMS32 _IOR(MGSL_MAGIC_IOC,1,struct MGSL_PARAMS32) -#endif -#endif /* _SYNCLINK_H_ */ diff --git a/include/uapi/linux/synclink.h b/include/uapi/linux/synclink.h deleted file mode 100644 index 62f32d4e1021..000000000000 --- a/include/uapi/linux/synclink.h +++ /dev/null @@ -1,301 +0,0 @@ -/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ -/* - * SyncLink Multiprotocol Serial Adapter Driver - * - * $Id: synclink.h,v 3.14 2006/07/17 20:15:43 paulkf Exp $ - * - * Copyright (C) 1998-2000 by Microgate Corporation - * - * Redistribution of this file is permitted under - * the terms of the GNU Public License (GPL) - */ - -#ifndef _UAPI_SYNCLINK_H_ -#define _UAPI_SYNCLINK_H_ -#define SYNCLINK_H_VERSION 3.6 - -#include - -#define BIT0 0x0001 -#define BIT1 0x0002 -#define BIT2 0x0004 -#define BIT3 0x0008 -#define BIT4 0x0010 -#define BIT5 0x0020 -#define BIT6 0x0040 -#define BIT7 0x0080 -#define BIT8 0x0100 -#define BIT9 0x0200 -#define BIT10 0x0400 -#define BIT11 0x0800 -#define BIT12 0x1000 -#define BIT13 0x2000 -#define BIT14 0x4000 -#define BIT15 0x8000 -#define BIT16 0x00010000 -#define BIT17 0x00020000 -#define BIT18 0x00040000 -#define BIT19 0x00080000 -#define BIT20 0x00100000 -#define BIT21 0x00200000 -#define BIT22 0x00400000 -#define BIT23 0x00800000 -#define BIT24 0x01000000 -#define BIT25 0x02000000 -#define BIT26 0x04000000 -#define BIT27 0x08000000 -#define BIT28 0x10000000 -#define BIT29 0x20000000 -#define BIT30 0x40000000 -#define BIT31 0x80000000 - - -#define HDLC_MAX_FRAME_SIZE 65535 -#define MAX_ASYNC_TRANSMIT 4096 -#define MAX_ASYNC_BUFFER_SIZE 4096 - -#define ASYNC_PARITY_NONE 0 -#define ASYNC_PARITY_EVEN 1 -#define ASYNC_PARITY_ODD 2 -#define ASYNC_PARITY_SPACE 3 - -#define HDLC_FLAG_UNDERRUN_ABORT7 0x0000 -#define HDLC_FLAG_UNDERRUN_ABORT15 0x0001 -#define HDLC_FLAG_UNDERRUN_FLAG 0x0002 -#define HDLC_FLAG_UNDERRUN_CRC 0x0004 -#define HDLC_FLAG_SHARE_ZERO 0x0010 -#define HDLC_FLAG_AUTO_CTS 0x0020 -#define HDLC_FLAG_AUTO_DCD 0x0040 -#define HDLC_FLAG_AUTO_RTS 0x0080 -#define HDLC_FLAG_RXC_DPLL 0x0100 -#define HDLC_FLAG_RXC_BRG 0x0200 -#define HDLC_FLAG_RXC_TXCPIN 0x8000 -#define HDLC_FLAG_RXC_RXCPIN 0x0000 -#define HDLC_FLAG_TXC_DPLL 0x0400 -#define HDLC_FLAG_TXC_BRG 0x0800 -#define HDLC_FLAG_TXC_TXCPIN 0x0000 -#define HDLC_FLAG_TXC_RXCPIN 0x0008 -#define HDLC_FLAG_DPLL_DIV8 0x1000 -#define HDLC_FLAG_DPLL_DIV16 0x2000 -#define HDLC_FLAG_DPLL_DIV32 0x0000 -#define HDLC_FLAG_HDLC_LOOPMODE 0x4000 - -#define HDLC_CRC_NONE 0 -#define HDLC_CRC_16_CCITT 1 -#define HDLC_CRC_32_CCITT 2 -#define HDLC_CRC_MASK 0x00ff -#define HDLC_CRC_RETURN_EX 0x8000 - -#define RX_OK 0 -#define RX_CRC_ERROR 1 - -#define HDLC_TXIDLE_FLAGS 0 -#define HDLC_TXIDLE_ALT_ZEROS_ONES 1 -#define HDLC_TXIDLE_ZEROS 2 -#define HDLC_TXIDLE_ONES 3 -#define HDLC_TXIDLE_ALT_MARK_SPACE 4 -#define HDLC_TXIDLE_SPACE 5 -#define HDLC_TXIDLE_MARK 6 -#define HDLC_TXIDLE_CUSTOM_8 0x10000000 -#define HDLC_TXIDLE_CUSTOM_16 0x20000000 - -#define HDLC_ENCODING_NRZ 0 -#define HDLC_ENCODING_NRZB 1 -#define HDLC_ENCODING_NRZI_MARK 2 -#define HDLC_ENCODING_NRZI_SPACE 3 -#define HDLC_ENCODING_NRZI HDLC_ENCODING_NRZI_SPACE -#define HDLC_ENCODING_BIPHASE_MARK 4 -#define HDLC_ENCODING_BIPHASE_SPACE 5 -#define HDLC_ENCODING_BIPHASE_LEVEL 6 -#define HDLC_ENCODING_DIFF_BIPHASE_LEVEL 7 - -#define HDLC_PREAMBLE_LENGTH_8BITS 0 -#define HDLC_PREAMBLE_LENGTH_16BITS 1 -#define HDLC_PREAMBLE_LENGTH_32BITS 2 -#define HDLC_PREAMBLE_LENGTH_64BITS 3 - -#define HDLC_PREAMBLE_PATTERN_NONE 0 -#define HDLC_PREAMBLE_PATTERN_ZEROS 1 -#define HDLC_PREAMBLE_PATTERN_FLAGS 2 -#define HDLC_PREAMBLE_PATTERN_10 3 -#define HDLC_PREAMBLE_PATTERN_01 4 -#define HDLC_PREAMBLE_PATTERN_ONES 5 - -#define MGSL_MODE_ASYNC 1 -#define MGSL_MODE_HDLC 2 -#define MGSL_MODE_MONOSYNC 3 -#define MGSL_MODE_BISYNC 4 -#define MGSL_MODE_RAW 6 -#define MGSL_MODE_BASE_CLOCK 7 -#define MGSL_MODE_XSYNC 8 - -#define MGSL_BUS_TYPE_ISA 1 -#define MGSL_BUS_TYPE_EISA 2 -#define MGSL_BUS_TYPE_PCI 5 - -#define MGSL_INTERFACE_MASK 0xf -#define MGSL_INTERFACE_DISABLE 0 -#define MGSL_INTERFACE_RS232 1 -#define MGSL_INTERFACE_V35 2 -#define MGSL_INTERFACE_RS422 3 -#define MGSL_INTERFACE_RTS_EN 0x10 -#define MGSL_INTERFACE_LL 0x20 -#define MGSL_INTERFACE_RL 0x40 -#define MGSL_INTERFACE_MSB_FIRST 0x80 - -typedef struct _MGSL_PARAMS -{ - /* Common */ - - unsigned long mode; /* Asynchronous or HDLC */ - unsigned char loopback; /* internal loopback mode */ - - /* HDLC Only */ - - unsigned short flags; - unsigned char encoding; /* NRZ, NRZI, etc. */ - unsigned long clock_speed; /* external clock speed in bits per second */ - unsigned char addr_filter; /* receive HDLC address filter, 0xFF = disable */ - unsigned short crc_type; /* None, CRC16-CCITT, or CRC32-CCITT */ - unsigned char preamble_length; - unsigned char preamble; - - /* Async Only */ - - unsigned long data_rate; /* bits per second */ - unsigned char data_bits; /* 7 or 8 data bits */ - unsigned char stop_bits; /* 1 or 2 stop bits */ - unsigned char parity; /* none, even, or odd */ - -} MGSL_PARAMS, *PMGSL_PARAMS; - -#define MICROGATE_VENDOR_ID 0x13c0 -#define SYNCLINK_DEVICE_ID 0x0010 -#define MGSCC_DEVICE_ID 0x0020 -#define SYNCLINK_SCA_DEVICE_ID 0x0030 -#define SYNCLINK_GT_DEVICE_ID 0x0070 -#define SYNCLINK_GT4_DEVICE_ID 0x0080 -#define SYNCLINK_AC_DEVICE_ID 0x0090 -#define SYNCLINK_GT2_DEVICE_ID 0x00A0 -#define MGSL_MAX_SERIAL_NUMBER 30 - -/* -** device diagnostics status -*/ - -#define DiagStatus_OK 0 -#define DiagStatus_AddressFailure 1 -#define DiagStatus_AddressConflict 2 -#define DiagStatus_IrqFailure 3 -#define DiagStatus_IrqConflict 4 -#define DiagStatus_DmaFailure 5 -#define DiagStatus_DmaConflict 6 -#define DiagStatus_PciAdapterNotFound 7 -#define DiagStatus_CantAssignPciResources 8 -#define DiagStatus_CantAssignPciMemAddr 9 -#define DiagStatus_CantAssignPciIoAddr 10 -#define DiagStatus_CantAssignPciIrq 11 -#define DiagStatus_MemoryError 12 - -#define SerialSignal_DCD 0x01 /* Data Carrier Detect */ -#define SerialSignal_TXD 0x02 /* Transmit Data */ -#define SerialSignal_RI 0x04 /* Ring Indicator */ -#define SerialSignal_RXD 0x08 /* Receive Data */ -#define SerialSignal_CTS 0x10 /* Clear to Send */ -#define SerialSignal_RTS 0x20 /* Request to Send */ -#define SerialSignal_DSR 0x40 /* Data Set Ready */ -#define SerialSignal_DTR 0x80 /* Data Terminal Ready */ - - -/* - * Counters of the input lines (CTS, DSR, RI, CD) interrupts - */ -struct mgsl_icount { - __u32 cts, dsr, rng, dcd, tx, rx; - __u32 frame, parity, overrun, brk; - __u32 buf_overrun; - __u32 txok; - __u32 txunder; - __u32 txabort; - __u32 txtimeout; - __u32 rxshort; - __u32 rxlong; - __u32 rxabort; - __u32 rxover; - __u32 rxcrc; - __u32 rxok; - __u32 exithunt; - __u32 rxidle; -}; - -struct gpio_desc { - __u32 state; - __u32 smask; - __u32 dir; - __u32 dmask; -}; - -#define DEBUG_LEVEL_DATA 1 -#define DEBUG_LEVEL_ERROR 2 -#define DEBUG_LEVEL_INFO 3 -#define DEBUG_LEVEL_BH 4 -#define DEBUG_LEVEL_ISR 5 - -/* -** Event bit flags for use with MgslWaitEvent -*/ - -#define MgslEvent_DsrActive 0x0001 -#define MgslEvent_DsrInactive 0x0002 -#define MgslEvent_Dsr 0x0003 -#define MgslEvent_CtsActive 0x0004 -#define MgslEvent_CtsInactive 0x0008 -#define MgslEvent_Cts 0x000c -#define MgslEvent_DcdActive 0x0010 -#define MgslEvent_DcdInactive 0x0020 -#define MgslEvent_Dcd 0x0030 -#define MgslEvent_RiActive 0x0040 -#define MgslEvent_RiInactive 0x0080 -#define MgslEvent_Ri 0x00c0 -#define MgslEvent_ExitHuntMode 0x0100 -#define MgslEvent_IdleReceived 0x0200 - -/* Private IOCTL codes: - * - * MGSL_IOCSPARAMS set MGSL_PARAMS structure values - * MGSL_IOCGPARAMS get current MGSL_PARAMS structure values - * MGSL_IOCSTXIDLE set current transmit idle mode - * MGSL_IOCGTXIDLE get current transmit idle mode - * MGSL_IOCTXENABLE enable or disable transmitter - * MGSL_IOCRXENABLE enable or disable receiver - * MGSL_IOCTXABORT abort transmitting frame (HDLC) - * MGSL_IOCGSTATS return current statistics - * MGSL_IOCWAITEVENT wait for specified event to occur - * MGSL_LOOPTXDONE transmit in HDLC LoopMode done - * MGSL_IOCSIF set the serial interface type - * MGSL_IOCGIF get the serial interface type - */ -#define MGSL_MAGIC_IOC 'm' -#define MGSL_IOCSPARAMS _IOW(MGSL_MAGIC_IOC,0,struct _MGSL_PARAMS) -#define MGSL_IOCGPARAMS _IOR(MGSL_MAGIC_IOC,1,struct _MGSL_PARAMS) -#define MGSL_IOCSTXIDLE _IO(MGSL_MAGIC_IOC,2) -#define MGSL_IOCGTXIDLE _IO(MGSL_MAGIC_IOC,3) -#define MGSL_IOCTXENABLE _IO(MGSL_MAGIC_IOC,4) -#define MGSL_IOCRXENABLE _IO(MGSL_MAGIC_IOC,5) -#define MGSL_IOCTXABORT _IO(MGSL_MAGIC_IOC,6) -#define MGSL_IOCGSTATS _IO(MGSL_MAGIC_IOC,7) -#define MGSL_IOCWAITEVENT _IOWR(MGSL_MAGIC_IOC,8,int) -#define MGSL_IOCCLRMODCOUNT _IO(MGSL_MAGIC_IOC,15) -#define MGSL_IOCLOOPTXDONE _IO(MGSL_MAGIC_IOC,9) -#define MGSL_IOCSIF _IO(MGSL_MAGIC_IOC,10) -#define MGSL_IOCGIF _IO(MGSL_MAGIC_IOC,11) -#define MGSL_IOCSGPIO _IOW(MGSL_MAGIC_IOC,16,struct gpio_desc) -#define MGSL_IOCGGPIO _IOR(MGSL_MAGIC_IOC,17,struct gpio_desc) -#define MGSL_IOCWAITGPIO _IOWR(MGSL_MAGIC_IOC,18,struct gpio_desc) -#define MGSL_IOCSXSYNC _IO(MGSL_MAGIC_IOC, 19) -#define MGSL_IOCGXSYNC _IO(MGSL_MAGIC_IOC, 20) -#define MGSL_IOCSXCTRL _IO(MGSL_MAGIC_IOC, 21) -#define MGSL_IOCGXCTRL _IO(MGSL_MAGIC_IOC, 22) - - -#endif /* _UAPI_SYNCLINK_H_ */ -- cgit v1.3-14-g43fede From a789761de3053d25f03787ac40897dbea14ee368 Mon Sep 17 00:00:00 2001 From: Benjamin Welton Date: Mon, 9 Feb 2026 00:42:00 +0800 Subject: amd/amdkfd: Add kfd_ioctl_profiler to contain profiler kernel driver changes kfd_ioctl_profiler takes a similar approach to that of kfd_ioctl_dbg_trap (which contains debugger related IOCTL services) where kfd_ioctl_profiler will contain all profiler related IOCTL services. The IOCTL is designed to be expanded as needed to support additional profiler functionality. The current functionality of the IOCTL is to allow for profilers which need PMC counters from GPU devices to both signal to other profilers that may be on the system that the device has active PMC profiling taking place on it (multiple PMC profilers on the same device can result in corrupted counter data) and to setup the device to allow for the collection of SQ PMC data on all queues on the device. For PMC data for the SQ block (such as SQ_WAVES) to be available to a profiler, mmPERFCOUNT_ENABLE must be set on the queues. When profiling a single process, the profiler can inject PM4 packets into each queue to turn on PERFCOUNT_ENABLE. When profiling system wide, the profiler does not have this option and must have a way to turn on profiling for queues in which it cannot inject packets into directly. Accomplishing this requires a few steps: 1. Checking if the user has the necessary permissions to profile system wide on the device. This check uses the same check that linux perf uses to determine if a user has the necessary permissions to profile at this scope (primarily if the process has CAP_SYS_PERFMON or is root). 2. Locking the device for profiling. This is done by setting a lock bit on the device struct and storing the process that locked the device. 3. Iterating all queues on the device and issuing an MQD Update to enable perfcounting on the queues. 4. Actions to cleanup if the process exits or releases the lock. The IOCTL also contains a link to the existing PC Sampling IOCTL as well. This is per a suggestion that we should potentially remove the PC Sampling IOCTL to have it be a part of the profiler IOCTL. This is a future change. In addition, we do expect to expand the profiler IOCTL to include additional profiler functionality in the future (which necessitates the use of a version number). v2: sqaush in proper IOCTL number Proposed userpace support: https://github.com/ROCm/rocm-systems/commit/40abc95a6463a61bb318a67efd6d9cc3e5ee8839 Signed-off-by: Benjamin Welton Signed-off-by: Perry Yuan Acked-by: Kent Russell Reviewed-by: Yifan Zhang Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 82 ++++++++++++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_device.c | 4 ++ .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 25 +++++++ .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.h | 2 + drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 16 ++++- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 14 +++- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c | 8 ++- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 15 +++- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c | 11 +++ drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 7 ++ drivers/gpu/drm/amd/amdkfd/kfd_process.c | 11 +++ include/uapi/linux/kfd_ioctl.h | 28 +++++++- 12 files changed, 214 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index dd27d7ba2ee2..d18ec3671fda 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -21,6 +21,7 @@ * OTHER DEALINGS IN THE SOFTWARE. */ +#include #include #include #include @@ -3216,6 +3217,84 @@ static int kfd_ioctl_create_process(struct file *filep, struct kfd_process *p, v return 0; } +static inline uint32_t profile_lock_device(struct kfd_process *p, + uint32_t gpu_id, uint32_t op) +{ + struct kfd_process_device *pdd; + struct kfd_dev *kfd; + int status = -EINVAL; + + if (!p) + return -EINVAL; + + mutex_lock(&p->mutex); + pdd = kfd_process_device_data_by_id(p, gpu_id); + mutex_unlock(&p->mutex); + + if (!pdd || !pdd->dev || !pdd->dev->kfd) + return -EINVAL; + + kfd = pdd->dev->kfd; + + mutex_lock(&kfd->profiler_lock); + if (op == 1) { + if (!kfd->profiler_process) { + kfd->profiler_process = p; + status = 0; + } else if (kfd->profiler_process == p) { + status = -EALREADY; + } else { + status = -EBUSY; + } + } else if (op == 0 && kfd->profiler_process == p) { + kfd->profiler_process = NULL; + status = 0; + } + mutex_unlock(&kfd->profiler_lock); + + return status; +} + +static inline int kfd_profiler_pmc(struct kfd_process *p, + struct kfd_ioctl_pmc_settings *args) +{ + struct kfd_process_device *pdd; + struct device_queue_manager *dqm; + int status; + + /* Check if we have the correct permissions. */ + if (!perfmon_capable()) + return -EPERM; + + /* Lock/Unlock the device based on the parameter given in OP */ + status = profile_lock_device(p, args->gpu_id, args->lock); + if (status != 0) + return status; + + /* Enable/disable perfcount if requested */ + mutex_lock(&p->mutex); + pdd = kfd_process_device_data_by_id(p, args->gpu_id); + dqm = pdd->dev->dqm; + mutex_unlock(&p->mutex); + + dqm->ops.set_perfcount(dqm, args->perfcount_enable); + return status; +} + +static int kfd_ioctl_profiler(struct file *filep, struct kfd_process *p, void *data) +{ + struct kfd_ioctl_profiler_args *args = data; + + switch (args->op) { + case KFD_IOC_PROFILER_VERSION: + args->version = KFD_IOC_PROFILER_VERSION_NUM; + return 0; + case KFD_IOC_PROFILER_PMC: + return kfd_profiler_pmc(p, &args->pmc); + } + return -EINVAL; +} + #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ .validate = NULL, .cmd_drv = 0, .name = #ioctl} @@ -3342,6 +3421,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_CREATE_PROCESS, kfd_ioctl_create_process, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_PROFILER, + kfd_ioctl_profiler, 0), }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index b7f8f7ff8198..d649d8603e28 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -936,6 +936,9 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, svm_range_set_max_pages(kfd->adev); + kfd->profiler_process = NULL; + mutex_init(&kfd->profiler_lock); + kfd->init_complete = true; dev_info(kfd_device, "added device %x:%x\n", kfd->adev->pdev->vendor, kfd->adev->pdev->device); @@ -971,6 +974,7 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd) ida_destroy(&kfd->doorbell_ida); kfd_gtt_sa_fini(kfd); amdgpu_amdkfd_free_kernel_mem(kfd->adev, &kfd->gtt_mem); + mutex_destroy(&kfd->profiler_lock); } kfree(kfd); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index a9ac575537e5..c64a1e19fa3f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -324,6 +324,29 @@ static int remove_queue_mes_on_reset_option(struct device_queue_manager *dqm, st return r; } +static void set_perfcount(struct device_queue_manager *dqm, int enable) +{ + struct device_process_node *cur; + struct qcm_process_device *qpd; + struct queue *q; + struct mqd_update_info minfo = { 0 }; + + if (!dqm) + return; + + minfo.update_flag = (enable == 1 ? UPDATE_FLAG_PERFCOUNT_ENABLE : + UPDATE_FLAG_PERFCOUNT_DISABLE); + dqm_lock(dqm); + list_for_each_entry(cur, &dqm->queues, list) { + qpd = cur->qpd; + list_for_each_entry(q, &qpd->queues_list, list) { + pqm_update_mqd(qpd->pqm, q->properties.queue_id, + &minfo); + } + } + dqm_unlock(dqm); +} + static int remove_queue_mes(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd) { @@ -3113,6 +3136,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) dqm->ops.reset_queues = reset_queues_cpsch; dqm->ops.get_queue_checkpoint_info = get_queue_checkpoint_info; dqm->ops.checkpoint_mqd = checkpoint_mqd; + dqm->ops.set_perfcount = set_perfcount; break; case KFD_SCHED_POLICY_NO_HWS: /* initialize dqm for no cp scheduling */ @@ -3133,6 +3157,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) dqm->ops.get_wave_state = get_wave_state; dqm->ops.get_queue_checkpoint_info = get_queue_checkpoint_info; dqm->ops.checkpoint_mqd = checkpoint_mqd; + dqm->ops.set_perfcount = set_perfcount; break; default: dev_err(dev->adev->dev, "Invalid scheduling policy %d\n", dqm->sched_policy); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index a0323501c6b9..e0b6a47e7722 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -199,6 +199,8 @@ struct device_queue_manager_ops { const struct queue *q, void *mqd, void *ctl_stack); + void (*set_perfcount)(struct device_queue_manager *dqm, + int enable); }; struct device_queue_manager_asic_ops { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c index 77fb41e2486a..8e8ec266ca46 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c @@ -123,10 +123,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, */ m->cp_hqd_hq_scheduler0 = 1 << 14; - if (q->format == KFD_QUEUE_FORMAT_AQL) { + if (q->format == KFD_QUEUE_FORMAT_AQL) m->cp_hqd_aql_control = 1 << CP_HQD_AQL_CONTROL__CONTROL0__SHIFT; - } if (mm->dev->kfd->cwsr_enabled) { m->cp_hqd_persistent_state |= @@ -141,6 +140,12 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_wg_state_offset = q->ctl_stack_size; } + mutex_lock(&mm->dev->kfd->profiler_lock); + if (mm->dev->kfd->profiler_process != NULL) + m->compute_perfcount_enable = 1; + + mutex_unlock(&mm->dev->kfd->profiler_lock); + *mqd = m; if (gart_addr) *gart_addr = addr; @@ -220,6 +225,13 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, if (mm->dev->kfd->cwsr_enabled) m->cp_hqd_ctx_save_control = 0; + if (minfo) { + if (minfo->update_flag == UPDATE_FLAG_PERFCOUNT_ENABLE) + m->compute_perfcount_enable = 1; + else if (minfo->update_flag == UPDATE_FLAG_PERFCOUNT_DISABLE) + m->compute_perfcount_enable = 0; + } + update_cu_mask(mm, mqd, minfo); set_priority(m, q); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index a1e3cf2384dd..7568e7ed5244 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -163,10 +163,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, if (amdgpu_amdkfd_have_atomics_support(mm->dev->adev)) m->cp_hqd_hq_status0 |= 1 << 29; - if (q->format == KFD_QUEUE_FORMAT_AQL) { + if (q->format == KFD_QUEUE_FORMAT_AQL) m->cp_hqd_aql_control = 1 << CP_HQD_AQL_CONTROL__CONTROL0__SHIFT; - } if (mm->dev->kfd->cwsr_enabled) { m->cp_hqd_persistent_state |= @@ -181,6 +180,11 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_wg_state_offset = q->ctl_stack_size; } + mutex_lock(&mm->dev->kfd->profiler_lock); + if (mm->dev->kfd->profiler_process != NULL) + m->compute_perfcount_enable = 1; + mutex_unlock(&mm->dev->kfd->profiler_lock); + *mqd = m; if (gart_addr) *gart_addr = addr; @@ -258,6 +262,12 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, } if (mm->dev->kfd->cwsr_enabled) m->cp_hqd_ctx_save_control = 0; + if (minfo) { + if (minfo->update_flag == UPDATE_FLAG_PERFCOUNT_ENABLE) + m->compute_perfcount_enable = 1; + else if (minfo->update_flag == UPDATE_FLAG_PERFCOUNT_DISABLE) + m->compute_perfcount_enable = 0; + } update_cu_mask(mm, mqd, minfo); set_priority(m, q); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c index b3e122d7876e..8c815f129614 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c @@ -138,10 +138,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, if (amdgpu_amdkfd_have_atomics_support(mm->dev->adev)) m->cp_hqd_hq_status0 |= 1 << 29; - if (q->format == KFD_QUEUE_FORMAT_AQL) { + if (q->format == KFD_QUEUE_FORMAT_AQL) m->cp_hqd_aql_control = 1 << CP_HQD_AQL_CONTROL__CONTROL0__SHIFT; - } if (mm->dev->kfd->cwsr_enabled) { m->cp_hqd_persistent_state |= @@ -156,6 +155,11 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_wg_state_offset = q->ctl_stack_size; } + mutex_lock(&mm->dev->kfd->profiler_lock); + if (mm->dev->kfd->profiler_process != NULL) + m->compute_perfcount_enable = 1; + mutex_unlock(&mm->dev->kfd->profiler_lock); + *mqd = m; if (gart_addr) *gart_addr = addr; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index e8f97de9d6e4..56a7679ca98d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -227,10 +227,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_aql_control = 1 << CP_HQD_AQL_CONTROL__CONTROL0__SHIFT; - if (q->tba_addr) { + if (q->tba_addr) m->compute_pgm_rsrc2 |= (1 << COMPUTE_PGM_RSRC2__TRAP_PRESENT__SHIFT); - } if (mm->dev->kfd->cwsr_enabled && q->ctx_save_restore_area_address) { m->cp_hqd_persistent_state |= @@ -245,6 +244,11 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_wg_state_offset = q->ctl_stack_size; } + mutex_lock(&mm->dev->kfd->profiler_lock); + if (mm->dev->kfd->profiler_process != NULL) + m->compute_perfcount_enable = 1; + mutex_unlock(&mm->dev->kfd->profiler_lock); + *mqd = m; if (gart_addr) *gart_addr = addr; @@ -327,6 +331,13 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, if (mm->dev->kfd->cwsr_enabled && q->ctx_save_restore_area_address) m->cp_hqd_ctx_save_control = 0; + if (minfo) { + if (minfo->update_flag == UPDATE_FLAG_PERFCOUNT_ENABLE) + m->compute_perfcount_enable = 1; + else if (minfo->update_flag == UPDATE_FLAG_PERFCOUNT_DISABLE) + m->compute_perfcount_enable = 0; + } + if (KFD_GC_VERSION(mm->dev) != IP_VERSION(9, 4, 3) && KFD_GC_VERSION(mm->dev) != IP_VERSION(9, 4, 4) && KFD_GC_VERSION(mm->dev) != IP_VERSION(9, 5, 0)) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c index 431a20323146..c86779af323b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c @@ -148,6 +148,11 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_wg_state_offset = q->ctl_stack_size; } + mutex_lock(&mm->dev->kfd->profiler_lock); + if (mm->dev->kfd->profiler_process != NULL) + m->compute_perfcount_enable = 1; + mutex_unlock(&mm->dev->kfd->profiler_lock); + *mqd = m; if (gart_addr) *gart_addr = addr; @@ -230,6 +235,12 @@ static void __update_mqd(struct mqd_manager *mm, void *mqd, m->cp_hqd_ctx_save_control = atc_bit << CP_HQD_CTX_SAVE_CONTROL__ATC__SHIFT | mtype << CP_HQD_CTX_SAVE_CONTROL__MTYPE__SHIFT; + if (minfo) { + if (minfo->update_flag == UPDATE_FLAG_PERFCOUNT_ENABLE) + m->compute_perfcount_enable = 1; + else if (minfo->update_flag == UPDATE_FLAG_PERFCOUNT_DISABLE) + m->compute_perfcount_enable = 0; + } update_cu_mask(mm, mqd, minfo); set_priority(m, q); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 9fe5c66d8013..903386e0740b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -383,6 +383,11 @@ struct kfd_dev { int kfd_dev_lock; atomic_t kfd_processes_count; + + /* Lock for profiler process */ + struct mutex profiler_lock; + /* Process currently holding the lock */ + struct kfd_process *profiler_process; }; enum kfd_mempool { @@ -556,6 +561,8 @@ enum mqd_update_flag { UPDATE_FLAG_DBG_WA_ENABLE = 1, UPDATE_FLAG_DBG_WA_DISABLE = 2, UPDATE_FLAG_IS_GWS = 4, /* quirk for gfx9 IP */ + UPDATE_FLAG_PERFCOUNT_ENABLE = 5, + UPDATE_FLAG_PERFCOUNT_DISABLE = 6, }; struct mqd_update_info { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 9228e4a949ed..1a8cb512dfe3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1106,6 +1106,16 @@ static void kfd_process_free_outstanding_kfd_bos(struct kfd_process *p) kfd_process_device_free_bos(p->pdds[i]); } +static void kfd_process_profiler_release(struct kfd_process *p, struct kfd_process_device *pdd) +{ + mutex_lock(&pdd->dev->kfd->profiler_lock); + if (pdd->dev->kfd->profiler_process == p) { + pdd->qpd.dqm->ops.set_perfcount(pdd->qpd.dqm, 0); + pdd->dev->kfd->profiler_process = NULL; + } + mutex_unlock(&pdd->dev->kfd->profiler_lock); +} + static void kfd_process_destroy_pdds(struct kfd_process *p) { int i; @@ -1117,6 +1127,7 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) pr_debug("Releasing pdd (topology id %d, for pid %d)\n", pdd->dev->id, p->lead_thread->pid); + kfd_process_profiler_release(p, pdd); kfd_process_device_destroy_cwsr_dgpu(pdd); kfd_process_device_destroy_ib_mem(pdd); diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index e72359370857..cc3ed0765c83 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -1558,6 +1558,29 @@ struct kfd_ioctl_dbg_trap_args { }; }; +#define KFD_IOC_PROFILER_VERSION_NUM 1 +enum kfd_profiler_ops { + KFD_IOC_PROFILER_PMC = 0, + KFD_IOC_PROFILER_VERSION = 2, +}; + +/** + * Enables/Disables GPU Specific profiler settings + */ +struct kfd_ioctl_pmc_settings { + __u32 gpu_id; /* This is the user_gpu_id */ + __u32 lock; /* Lock GPU for Profiling */ + __u32 perfcount_enable; /* Force Perfcount Enable for queues on GPU */ +}; + +struct kfd_ioctl_profiler_args { + __u32 op; /* kfd_profiler_op */ + union { + struct kfd_ioctl_pmc_settings pmc; + __u32 version; /* KFD_IOC_PROFILER_VERSION_NUM */ + }; +}; + #define AMDKFD_IOCTL_BASE 'K' #define AMDKFD_IO(nr) _IO(AMDKFD_IOCTL_BASE, nr) #define AMDKFD_IOR(nr, type) _IOR(AMDKFD_IOCTL_BASE, nr, type) @@ -1681,7 +1704,10 @@ struct kfd_ioctl_dbg_trap_args { #define AMDKFD_IOC_CREATE_PROCESS \ AMDKFD_IO(0x27) +#define AMDKFD_IOC_PROFILER \ + AMDKFD_IOWR(0x28, struct kfd_ioctl_profiler_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x28 +#define AMDKFD_COMMAND_END 0x29 #endif -- cgit v1.3-14-g43fede From dd61e27535a6f5cfb32a847b282d2e3d5aebf46f Mon Sep 17 00:00:00 2001 From: Perry Yuan Date: Mon, 9 Feb 2026 00:42:07 +0800 Subject: drm/amdkfd: Add PTL control IOCTL Option and unify refcount logic Introduce a new IOCTL option to allow userspace explicit control over the Peak Tops Limiter (PTL) state for profiling Link: https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-sdk Signed-off-by: Perry Yuan Reviewed-by: Yifan Zhang Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 2 + drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 102 +++++++++++++++++++++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 8 +++ drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 ++ drivers/gpu/drm/amd/include/amdgpu_ptl.h | 2 + include/uapi/linux/kfd_ioctl.h | 7 +++ 6 files changed, 125 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 467a3dbe1bfa..aab6a4de54fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -2400,6 +2400,8 @@ static int gfx_v9_4_3_perf_monitor_ptl_init(struct amdgpu_device *adev, bool ena ptl->hw_supported = true; + atomic_set(&ptl->disable_ref, 0); + return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index fc00d0418684..883de31df04d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1774,6 +1774,104 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data) } #endif +static int kfd_ptl_control(struct kfd_process_device *pdd, bool enable) +{ + struct amdgpu_device *adev = pdd->dev->adev; + struct amdgpu_ptl *ptl = &adev->psp.ptl; + enum amdgpu_ptl_fmt pref_format1 = ptl->fmt1; + enum amdgpu_ptl_fmt pref_format2 = ptl->fmt2; + uint32_t ptl_state = enable ? 1 : 0; + int ret; + + if (!ptl->hw_supported) + return -EOPNOTSUPP; + + if (!pdd->dev->kfd2kgd || !pdd->dev->kfd2kgd->ptl_ctrl) + return -EOPNOTSUPP; + + ret = pdd->dev->kfd2kgd->ptl_ctrl(adev, PSP_PTL_PERF_MON_SET, + &ptl_state, + &pref_format1, + &pref_format2); + return ret; +} + +int kfd_ptl_disable_request(struct kfd_process_device *pdd, + struct kfd_process *p) +{ + struct amdgpu_device *adev = pdd->dev->adev; + struct amdgpu_ptl *ptl = &adev->psp.ptl; + int ret = 0; + + mutex_lock(&ptl->mutex); + + if (pdd->ptl_disable_req) + goto out; + + if (atomic_inc_return(&ptl->disable_ref) == 1) { + ret = kfd_ptl_control(pdd, false); + if (ret) { + atomic_dec(&ptl->disable_ref); + dev_warn(pdd->dev->adev->dev, + "failed to disable PTL\n"); + goto out; + } + } + pdd->ptl_disable_req = true; + +out: + mutex_unlock(&ptl->mutex); + return ret; +} + +int kfd_ptl_disable_release(struct kfd_process_device *pdd, + struct kfd_process *p) +{ + struct amdgpu_device *adev = pdd->dev->adev; + struct amdgpu_ptl *ptl = &adev->psp.ptl; + int ret = 0; + + mutex_lock(&ptl->mutex); + + if (!pdd->ptl_disable_req) + goto out; + + if (atomic_dec_return(&ptl->disable_ref) == 0) { + ret = kfd_ptl_control(pdd, true); + if (ret) { + atomic_inc(&ptl->disable_ref); + dev_warn(adev->dev, "Failed to enable PTL on release: %d\n", ret); + goto out; + } + } + pdd->ptl_disable_req = false; + +out: + mutex_unlock(&ptl->mutex); + return ret; +} + +static int kfd_profiler_ptl_control(struct kfd_process *p, + struct kfd_ioctl_ptl_control *args) +{ + struct kfd_process_device *pdd; + int ret; + + mutex_lock(&p->mutex); + pdd = kfd_process_device_data_by_id(p, args->gpu_id); + mutex_unlock(&p->mutex); + + if (!pdd || !pdd->dev || !pdd->dev->kfd) + return -EINVAL; + + if (args->enable == 0) + ret = kfd_ptl_disable_request(pdd, p); + else + ret = kfd_ptl_disable_release(pdd, p); + + return ret; +} + static int criu_checkpoint_process(struct kfd_process *p, uint8_t __user *user_priv_data, uint64_t *priv_offset) @@ -3242,6 +3340,7 @@ static inline uint32_t profile_lock_device(struct kfd_process *p, if (!kfd->profiler_process) { kfd->profiler_process = p; status = 0; + kfd_ptl_disable_request(pdd, p); } else if (kfd->profiler_process == p) { status = -EALREADY; } else { @@ -3250,6 +3349,7 @@ static inline uint32_t profile_lock_device(struct kfd_process *p, } else if (op == 0 && kfd->profiler_process == p) { kfd->profiler_process = NULL; status = 0; + kfd_ptl_disable_release(pdd, p); } mutex_unlock(&kfd->profiler_lock); @@ -3292,6 +3392,8 @@ static int kfd_ioctl_profiler(struct file *filep, struct kfd_process *p, void *d return 0; case KFD_IOC_PROFILER_PMC: return kfd_profiler_pmc(p, &args->pmc); + case KFD_IOC_PROFILER_PTL_CONTROL: + return kfd_profiler_ptl_control(p, &args->ptl); } return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 903386e0740b..482bcfa10f82 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -872,6 +872,8 @@ struct kfd_process_device { bool has_reset_queue; u32 pasid; + /* Indicates this process has requested PTL stay disabled */ + bool ptl_disable_req; }; #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd) @@ -1603,6 +1605,12 @@ static inline bool kfd_is_first_node(struct kfd_node *node) return (node == node->kfd->nodes[0]); } +/* PTL support */ +int kfd_ptl_disable_request(struct kfd_process_device *pdd, + struct kfd_process *p); +int kfd_ptl_disable_release(struct kfd_process_device *pdd, + struct kfd_process *p); + /* Debugfs */ #if defined(CONFIG_DEBUG_FS) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 1a8cb512dfe3..368283d53077 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1128,6 +1128,10 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) pr_debug("Releasing pdd (topology id %d, for pid %d)\n", pdd->dev->id, p->lead_thread->pid); kfd_process_profiler_release(p, pdd); + + if (pdd->ptl_disable_req) + kfd_ptl_disable_release(pdd, p); + kfd_process_device_destroy_cwsr_dgpu(pdd); kfd_process_device_destroy_ib_mem(pdd); diff --git a/drivers/gpu/drm/amd/include/amdgpu_ptl.h b/drivers/gpu/drm/amd/include/amdgpu_ptl.h index ffed443a14ae..9e63a9a9680a 100644 --- a/drivers/gpu/drm/amd/include/amdgpu_ptl.h +++ b/drivers/gpu/drm/amd/include/amdgpu_ptl.h @@ -39,6 +39,8 @@ struct amdgpu_ptl { enum amdgpu_ptl_fmt fmt2; bool enabled; bool hw_supported; + /* PTL disable reference counting */ + atomic_t disable_ref; struct mutex mutex; }; diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index cc3ed0765c83..1a94d512df35 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -1562,6 +1562,7 @@ struct kfd_ioctl_dbg_trap_args { enum kfd_profiler_ops { KFD_IOC_PROFILER_PMC = 0, KFD_IOC_PROFILER_VERSION = 2, + KFD_IOC_PROFILER_PTL_CONTROL = 3, }; /** @@ -1573,10 +1574,16 @@ struct kfd_ioctl_pmc_settings { __u32 perfcount_enable; /* Force Perfcount Enable for queues on GPU */ }; +struct kfd_ioctl_ptl_control { + __u32 gpu_id; /* user_gpu_id */ + __u32 enable; /* set 1 to enable PTL, set 0 to disable PTL */ +}; + struct kfd_ioctl_profiler_args { __u32 op; /* kfd_profiler_op */ union { struct kfd_ioctl_pmc_settings pmc; + struct kfd_ioctl_ptl_control ptl; __u32 version; /* KFD_IOC_PROFILER_VERSION_NUM */ }; }; -- cgit v1.3-14-g43fede From c62c076d2d64ead542c961cabed0f9467d7d6026 Mon Sep 17 00:00:00 2001 From: Perry Yuan Date: Wed, 15 Apr 2026 10:34:03 +0800 Subject: drm/amdkfd: bump KFD ioctl minor version to 1.23 Bump `KFD_IOCTL_MINOR_VERSION` from 22 to 23 and document version 1.23 in `kfd_ioctl.h` so userspace can detect profiler ioctl support. Signed-off-by: Perry Yuan Suggested-by: Alex Deucher Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 1a94d512df35..9584b5aab727 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -48,9 +48,10 @@ * - 1.20 - Trap handler support for expert scheduling mode available * - 1.21 - Debugger support to subscribe to LDS out-of-address exceptions * - 1.22 - Add queue creation with metadata ring base address + * - 1.23 - Add profiler control ioctl to enable/disable profiler on a process */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 22 +#define KFD_IOCTL_MINOR_VERSION 23 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.3-14-g43fede From f28771c0691bcb7f477a0f35550b17b88c32dea8 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Tue, 12 May 2026 23:31:50 +0800 Subject: bpf: Extend BPF syscall with common attributes support Add generic BPF syscall support for passing common attributes. The initial set of common attributes includes: 1. 'log_buf': User-provided buffer for storing logs. 2. 'log_size': Size of the log buffer. 3. 'log_level': Log verbosity level. 4. 'log_true_size': Actual log size reported by kernel. The common-attribute pointer and its size are passed as the 4th and 5th syscall arguments. A new command bit, 'BPF_COMMON_ATTRS' ('1 << 16'), indicates that common attributes are supplied. This commit adds syscall and uapi plumbing. Command-specific handling is added in follow-up patches. Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20260512153157.28382-2-leon.hwang@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/syscalls.h | 3 ++- include/uapi/linux/bpf.h | 8 ++++++++ kernel/bpf/syscall.c | 25 +++++++++++++++++++++---- tools/include/uapi/linux/bpf.h | 8 ++++++++ 4 files changed, 39 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f5639d5ac331..50055ab73649 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -936,7 +936,8 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags, asmlinkage long sys_getrandom(char __user *buf, size_t count, unsigned int flags); asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); -asmlinkage long sys_bpf(int cmd, union bpf_attr __user *attr, unsigned int size); +asmlinkage long sys_bpf(int cmd, union bpf_attr __user *attr, unsigned int size, + struct bpf_common_attr __user *attr_common, unsigned int size_common); asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 552bc5d9afbd..aec171ccb6ef 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -994,6 +994,7 @@ enum bpf_cmd { BPF_PROG_STREAM_READ_BY_FD, BPF_PROG_ASSOC_STRUCT_OPS, __MAX_BPF_CMD, + BPF_COMMON_ATTRS = 1 << 16, /* Indicate carrying syscall common attrs. */ }; enum bpf_map_type { @@ -1500,6 +1501,13 @@ struct bpf_stack_build_id { }; }; +struct bpf_common_attr { + __aligned_u64 log_buf; + __u32 log_size; + __u32 log_level; + __u32 log_true_size; +}; + #define BPF_OBJ_NAME_LEN 16U enum { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3b1f0ba02f61..354f6f471a08 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -6211,8 +6211,10 @@ put_prog: return ret; } -static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) +static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size, + bpfptr_t uattr_common, unsigned int size_common) { + struct bpf_common_attr attr_common; union bpf_attr attr; int err; @@ -6226,6 +6228,20 @@ static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; + memset(&attr_common, 0, sizeof(attr_common)); + if (cmd & BPF_COMMON_ATTRS) { + err = bpf_check_uarg_tail_zero(uattr_common, sizeof(attr_common), size_common); + if (err) + return err; + + cmd &= ~BPF_COMMON_ATTRS; + size_common = min_t(u32, size_common, sizeof(attr_common)); + if (copy_from_bpfptr(&attr_common, uattr_common, size_common) != 0) + return -EFAULT; + } else { + size_common = 0; + } + err = security_bpf(cmd, &attr, size, uattr.is_kernel); if (err < 0) return err; @@ -6361,9 +6377,10 @@ static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) return err; } -SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +SYSCALL_DEFINE5(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size, + struct bpf_common_attr __user *, uattr_common, unsigned int, size_common) { - return __sys_bpf(cmd, USER_BPFPTR(uattr), size); + return __sys_bpf(cmd, USER_BPFPTR(uattr), size, USER_BPFPTR(uattr_common), size_common); } static bool syscall_prog_is_valid_access(int off, int size, @@ -6393,7 +6410,7 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) default: return -EINVAL; } - return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); + return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size, KERNEL_BPFPTR(NULL), 0); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 677be9a47347..37142e6d911a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -994,6 +994,7 @@ enum bpf_cmd { BPF_PROG_STREAM_READ_BY_FD, BPF_PROG_ASSOC_STRUCT_OPS, __MAX_BPF_CMD, + BPF_COMMON_ATTRS = 1 << 16, /* Indicate carrying syscall common attrs. */ }; enum bpf_map_type { @@ -1500,6 +1501,13 @@ struct bpf_stack_build_id { }; }; +struct bpf_common_attr { + __aligned_u64 log_buf; + __u32 log_size; + __u32 log_level; + __u32 log_true_size; +}; + #define BPF_OBJ_NAME_LEN 16U enum { -- cgit v1.3-14-g43fede From b588019e85f490696bf19f0747e93f14b1563927 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 May 2026 07:02:44 +0000 Subject: rtnetlink: add RTEXT_FILTER_NAME_ONLY support iproute2 can spend considerable amount of time in ll_init_map() or ll_link_get() to dump verbose netdev attributes, contributing to RTNL pressure. Add RTEXT_FILTER_NAME_ONLY new flag so that rtnl_fill_ifinfo() limits its output to: - struct nlmsghdr - IFLA_IFNAME - IFLA_PROP_LIST (alternate names) We can later avoid using RTNL when RTEXT_FILTER_NAME_ONLY is requested, as none of these attributes need RTNL. Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260511070244.971028-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/rtnetlink.h | 1 + net/core/rtnetlink.c | 31 ++++++++++++++++++++++--------- 2 files changed, 23 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index dab9493c791b..27265fd31e5f 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -840,6 +840,7 @@ enum { #define RTEXT_FILTER_CFM_CONFIG (1 << 5) #define RTEXT_FILTER_CFM_STATUS (1 << 6) #define RTEXT_FILTER_MST (1 << 7) +#define RTEXT_FILTER_NAME_ONLY (1 << 8) /* End of information exported to user level */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index df042da422ef..70fde922b371 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1295,7 +1295,12 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, size = NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ - + nla_total_size(IFALIASZ) /* IFLA_IFALIAS */ + + rtnl_prop_list_size(dev); + + if (ext_filter_mask & RTEXT_FILTER_NAME_ONLY) + return size; + + size += nla_total_size(IFALIASZ) /* IFLA_IFALIAS */ + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */ + nla_total_size_64bit(sizeof(struct rtnl_link_ifmap)) + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ @@ -1342,7 +1347,6 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */ + nla_total_size(4) /* IFLA_MIN_MTU */ + nla_total_size(4) /* IFLA_MAX_MTU */ - + rtnl_prop_list_size(dev) + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */ + rtnl_devlink_port_size(dev) + rtnl_dpll_pin_size(dev) @@ -1941,15 +1945,18 @@ static int rtnl_fill_alt_ifnames(struct sk_buff *skb, struct netdev_name_node *name_node; int count = 0; + rcu_read_lock(); list_for_each_entry_rcu(name_node, &dev->name_node->list, list) { - if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name)) + if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name)) { + rcu_read_unlock(); return -EMSGSIZE; + } count++; } + rcu_read_unlock(); return count; } -/* RCU protected. */ static int rtnl_fill_prop_list(struct sk_buff *skb, const struct net_device *dev) { @@ -2072,13 +2079,20 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, ifm->ifi_flags = netif_get_flags(dev); ifm->ifi_change = change; - if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) - goto nla_put_failure; - netdev_copy_name(dev, devname); if (nla_put_string(skb, IFLA_IFNAME, devname)) goto nla_put_failure; + if (rtnl_fill_prop_list(skb, dev)) + goto nla_put_failure; + + if (ext_filter_mask & RTEXT_FILTER_NAME_ONLY) + goto end; + + if (tgt_netnsid >= 0 && + nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_TXQLEN, READ_ONCE(dev->tx_queue_len)) || nla_put_u8(skb, IFLA_OPERSTATE, netif_running(dev) ? READ_ONCE(dev->operstate) : @@ -2191,8 +2205,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure_rcu; if (rtnl_fill_link_ifmap(skb, dev)) goto nla_put_failure_rcu; - if (rtnl_fill_prop_list(skb, dev)) - goto nla_put_failure_rcu; rcu_read_unlock(); if (dev->dev.parent && @@ -2211,6 +2223,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, if (rtnl_fill_dpll_pin(skb, dev)) goto nla_put_failure; +end: nlmsg_end(skb, nlh); return 0; -- cgit v1.3-14-g43fede From d5607f1fafd7eb72ed693b6a033d96221e870edd Mon Sep 17 00:00:00 2001 From: Christoph Böhmwalder Date: Wed, 13 May 2026 13:03:42 +0200 Subject: drbd: clean up UAPI headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit b1798910fc7f ("drbd: move UAPI headers to include/uapi/linux/") broke compilation on targets without a hosted libc: ./usr/include/linux/drbd.h:18:10: fatal error: sys/types.h: No such file or directory The underlying issue is that there were some constructs left over in those headers that don't belong in uapi. Drop the __KERNEL__-gated split in drbd.h. The !__KERNEL__ branch pulls in , and for symbols that the header does not actually reference; they were carried over from when this lived in include/linux/. Replace and the entire #ifdef block with the standard UAPI combo + , which provides __u32/__u64/__s32 and __{LITTLE,BIG}_ENDIAN_BITFIELD in both kernel and userspace contexts. drbd_limits.h references some enum values and the DRBD_PROT_C define from drbd.h, but does not include it. Add the missing include while we're here. Drop the unprefixed DEBUG_RANGE_CHECK from drbd_limits.h. It has no in-kernel users and pollutes the userspace namespace. Switch the drbd.h and drbd_limits.h include guards to the _UAPI_LINUX_* convention already used by drbd_genl.h. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202605101346.V2wwJqv1-lkp@intel.com/ Fixes: b1798910fc7f ("drbd: move UAPI headers to include/uapi/linux/") Signed-off-by: Christoph Böhmwalder Link: https://patch.msgid.link/20260513110343.3170338-1-christoph.boehmwalder@linbit.com Signed-off-by: Jens Axboe --- include/uapi/linux/drbd.h | 28 +++------------------------- include/uapi/linux/drbd_limits.h | 8 ++++---- 2 files changed, 7 insertions(+), 29 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/drbd.h b/include/uapi/linux/drbd.h index 5d4d677cf1ad..cf1ec3eb872f 100644 --- a/include/uapi/linux/drbd.h +++ b/include/uapi/linux/drbd.h @@ -11,32 +11,10 @@ */ -#ifndef DRBD_H -#define DRBD_H -#include - -#ifdef __KERNEL__ +#ifndef _UAPI_LINUX_DRBD_H +#define _UAPI_LINUX_DRBD_H #include #include -#else -#include -#include -#include - -/* Although the Linux source code makes a difference between - generic endianness and the bitfields' endianness, there is no - architecture as of Linux-2.6.24-rc4 where the bitfields' endianness - does not match the generic endianness. */ - -#if __BYTE_ORDER == __LITTLE_ENDIAN -#define __LITTLE_ENDIAN_BITFIELD -#elif __BYTE_ORDER == __BIG_ENDIAN -#define __BIG_ENDIAN_BITFIELD -#else -# error "sorry, weird endianness on this box" -#endif - -#endif enum drbd_io_error_p { EP_PASS_ON, /* FIXME should the better be named "Ignore"? */ @@ -432,4 +410,4 @@ enum drbd_state_info_bcast_reason { SIB_SYNC_PROGRESS = 5, }; -#endif +#endif /* _UAPI_LINUX_DRBD_H */ diff --git a/include/uapi/linux/drbd_limits.h b/include/uapi/linux/drbd_limits.h index a72a102d1ca7..acefe84bc602 100644 --- a/include/uapi/linux/drbd_limits.h +++ b/include/uapi/linux/drbd_limits.h @@ -11,10 +11,10 @@ * feedback about nonsense settings for certain configurable values. */ -#ifndef DRBD_LIMITS_H -#define DRBD_LIMITS_H 1 +#ifndef _UAPI_LINUX_DRBD_LIMITS_H +#define _UAPI_LINUX_DRBD_LIMITS_H -#define DEBUG_RANGE_CHECK 0 +#include #define DRBD_MINOR_COUNT_MIN 1U #define DRBD_MINOR_COUNT_MAX 255U @@ -248,4 +248,4 @@ #define DRBD_RS_DISCARD_GRANULARITY_DEF 0U /* disabled by default */ #define DRBD_RS_DISCARD_GRANULARITY_SCALE '1' /* bytes */ -#endif +#endif /* _UAPI_LINUX_DRBD_LIMITS_H */ -- cgit v1.3-14-g43fede From a2f6ed7b4873288d9e90e69199012857bed4bfa4 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sat, 9 May 2026 10:03:26 -0700 Subject: net/sched: netem: add per-impairment extended statistics Add 64-bit counters for each impairment netem applies (delay, loss, ECN marking, corruption, duplication, reordering) and for skb allocation failures during enqueue. Exposed through TCA_STATS_APP as struct tc_netem_xstats. Counters increment when an impairment is occurs, independent of later events that may mask its on-wire effect. Added allocation_errors (similar to sch_fq) to account for when impairment could not be applied due to memory pressure, etc. Signed-off-by: Stephen Hemminger Link: https://patch.msgid.link/20260509171123.307549-6-stephen@networkplumber.org Signed-off-by: Paolo Abeni --- include/uapi/linux/pkt_sched.h | 10 ++++++++ net/sched/sch_netem.c | 55 +++++++++++++++++++++++++++++++++++++----- 2 files changed, 59 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 66e8072f44df..490efd288526 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -569,6 +569,16 @@ struct tc_netem_gemodel { #define NETEM_DIST_SCALE 8192 #define NETEM_DIST_MAX 16384 +struct tc_netem_xstats { + __u64 delayed; /* packets delayed */ + __u64 dropped; /* packets dropped by loss model */ + __u64 corrupted; /* packets with bit errors injected */ + __u64 duplicated; /* duplicate packets generated */ + __u64 reordered; /* packets sent out of order */ + __u64 ecn_marked; /* packets ECN CE-marked (not dropped)*/ + __u64 allocation_errors; +}; + /* DRR */ enum { diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 1e9de2ba8891..6cd1838e09e7 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -152,6 +152,15 @@ struct netem_sched_data { u8 state; } clg; + /* Impairment counters */ + u64 delayed; + u64 dropped; + u64 corrupted; + u64 duplicated; + u64 ecn_marked; + u64 reordered; + u64 allocation_errors; + /* Cold tail: slot reschedule config and the watchdog timer. */ struct tc_netem_slot slot_config; struct qdisc_watchdog watchdog; @@ -462,16 +471,21 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb->prev = NULL; /* Random duplication */ - if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng)) + if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng)) { ++count; + WRITE_ONCE(q->duplicated, q->duplicated + 1); + } /* Drop packet? */ if (loss_event(q)) { - if (q->ecn && INET_ECN_set_ce(skb)) - qdisc_qstats_drop(sch); /* mark packet */ - else + if (q->ecn && INET_ECN_set_ce(skb)) { + WRITE_ONCE(q->ecn_marked, q->ecn_marked + 1); + } else { + WRITE_ONCE(q->dropped, q->dropped + 1); --count; + } } + if (count == 0) { qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); @@ -488,8 +502,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * If we need to duplicate packet, then clone it before * original is modified. */ - if (count > 1) + if (count > 1) { skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) + WRITE_ONCE(q->allocation_errors, q->allocation_errors + 1); + } /* * Randomized packet corruption. @@ -500,8 +517,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) { if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); - if (!skb) + if (!skb) { + WRITE_ONCE(q->allocation_errors, q->allocation_errors + 1); goto finish_segs; + } segs = skb->next; skb_mark_not_on_list(skb); @@ -510,11 +529,13 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb = skb_unshare(skb, GFP_ATOMIC); if (unlikely(!skb)) { + WRITE_ONCE(q->allocation_errors, q->allocation_errors + 1); qdisc_qstats_drop(sch); goto finish_segs; } if (skb_linearize(skb) || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))) { + WRITE_ONCE(q->allocation_errors, q->allocation_errors + 1); qdisc_drop(skb, sch, to_free); skb = NULL; goto finish_segs; @@ -523,6 +544,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb->len) { u32 offset = get_random_u32_below(skb->len); skb->data[offset] ^= 1 << get_random_u32_below(8); + WRITE_ONCE(q->corrupted, q->corrupted + 1); } } @@ -604,12 +626,16 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, cb->time_to_send = now + delay; ++q->counter; + if (delay) + WRITE_ONCE(q->delayed, q->delayed + 1); + tfifo_enqueue(skb, sch); } else { /* * Do re-ordering by putting one out of N packets at the front * of the queue. */ + WRITE_ONCE(q->reordered, q->reordered + 1); cb->time_to_send = ktime_get_ns(); q->counter = 0; @@ -1348,6 +1374,22 @@ nla_put_failure: return -1; } +static int netem_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct netem_sched_data *q = qdisc_priv(sch); + struct tc_netem_xstats st = { + .delayed = READ_ONCE(q->delayed), + .dropped = READ_ONCE(q->dropped), + .corrupted = READ_ONCE(q->corrupted), + .duplicated = READ_ONCE(q->duplicated), + .reordered = READ_ONCE(q->reordered), + .ecn_marked = READ_ONCE(q->ecn_marked), + .allocation_errors = READ_ONCE(q->allocation_errors), + }; + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + static int netem_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { @@ -1410,6 +1452,7 @@ static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .destroy = netem_destroy, .change = netem_change, .dump = netem_dump, + .dump_stats = netem_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("netem"); -- cgit v1.3-14-g43fede From 0c32db0761fef3d98d6e4d6d8ce02c40e914f4d8 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Mon, 11 May 2026 09:59:31 +0300 Subject: bridge: uapi: Add neigh_forward_grat netlink attributes Add netlink attributes for controlling gratuitous ARP and unsolicited NA forwarding when neighbor suppression is enabled. Add IFLA_BRPORT_NEIGH_FORWARD_GRAT for port-level control and BRIDGE_VLANDB_ENTRY_NEIGH_FORWARD_GRAT for per-VLAN control. The new attributes provide independent control of gratuitous ARP and unsolicited NA packets. Operators can enable forwarding for those packets for fast mobility across VTEPs while keeping general neighbor suppression active. Reviewed-by: Ido Schimmel Signed-off-by: Danielle Ratson Link: https://patch.msgid.link/20260511065936.4173106-2-danieller@nvidia.com Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/rt-link.yaml | 3 +++ include/uapi/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 17 +++++++++++++++++ net/core/rtnetlink.c | 2 +- 4 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index f23aa5f229c5..79c89f204415 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -1700,6 +1700,9 @@ attribute-sets: - name: backup-nhid type: u32 + - + name: neigh-forward-grat + type: u8 - name: linkinfo-gre-attrs name-prefix: ifla-gre- diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index e52f8207ab27..21a700c02ef7 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -526,6 +526,7 @@ enum { BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS, + BRIDGE_VLANDB_ENTRY_NEIGH_FORWARD_GRAT, __BRIDGE_VLANDB_ENTRY_MAX, }; #define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 79ce4bc24cba..46413392b402 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1085,6 +1085,22 @@ enum { * Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS* * is enabled for a given port. * + * @IFLA_BRPORT_NEIGH_FORWARD_GRAT + * Controls whether gratuitous ARP packets and unsolicited Neighbor + * Advertisement packets are forwarded on a given port even when neighbor + * suppression is enabled. + * By default this flag is off, meaning gratuitous ARP and unsolicited NA + * packets will be suppressed when neighbor suppression is enabled. + * Setting this flag to on allows these packets to be forwarded even + * when *IFLA_BRPORT_NEIGH_SUPPRESS* or *IFLA_BRPORT_NEIGH_VLAN_SUPPRESS* + * is enabled. + * + * Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS* + * or *IFLA_BRPORT_NEIGH_VLAN_SUPPRESS* is enabled for a given port. + * When *IFLA_BRPORT_NEIGH_VLAN_SUPPRESS* is set, this port-level flag is + * ignored and per-VLAN control is available via + * *BRIDGE_VLANDB_ENTRY_NEIGH_FORWARD_GRAT*. + * * @IFLA_BRPORT_BACKUP_NHID * The FDB nexthop object ID to attach to packets being redirected to a * backup port that has VLAN tunnel mapping enabled (via the @@ -1137,6 +1153,7 @@ enum { IFLA_BRPORT_MCAST_MAX_GROUPS, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, IFLA_BRPORT_BACKUP_NHID, + IFLA_BRPORT_NEIGH_FORWARD_GRAT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 70fde922b371..6a5e9ace55a0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -63,7 +63,7 @@ #include "dev.h" #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 44 +#define RTNL_SLAVE_MAX_TYPE 45 struct rtnl_link { rtnl_doit_func doit; -- cgit v1.3-14-g43fede From 899bea8248cee35d54760a5e7d61a76af8e64411 Mon Sep 17 00:00:00 2001 From: Shouvik Kar Date: Tue, 12 May 2026 16:32:42 +0530 Subject: io_uring/net: allow filtering on IORING_OP_CONNECT This adds custom filtering for IORING_OP_CONNECT, where the target family is always exposed, and (for AF_INET / AF_INET6) port and address are exposed. port and v4_addr are in network byte order so filter authors can compare against on-wire constants. Skip population unless addr_len covers the populated fields, to avoid leaking stale io_async_msghdr data on short connects. Signed-off-by: Shouvik Kar Link: https://patch.msgid.link/20260512110242.26219-1-auxcorelabs@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/bpf_filter.h | 16 +++++++++++++ io_uring/net.c | 41 ++++++++++++++++++++++++++++++++ io_uring/net.h | 7 ++++++ io_uring/opdef.c | 2 ++ 4 files changed, 66 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/bpf_filter.h b/include/uapi/linux/io_uring/bpf_filter.h index 1b461d792a7b..ce7d78ab13b3 100644 --- a/include/uapi/linux/io_uring/bpf_filter.h +++ b/include/uapi/linux/io_uring/bpf_filter.h @@ -27,6 +27,22 @@ struct io_uring_bpf_ctx { __u64 mode; __u64 resolve; } open; + /* + * For CONNECT: fields are populated only when addr_len covers + * them; unpopulated fields are zero from the caller-side memset + * in io_uring_populate_bpf_ctx(). port and v4_addr are network + * byte order. Filters may only issue BPF_LD|BPF_W|BPF_ABS at + * 4-byte aligned offsets; load + mask for sub-word fields. + */ + struct { + __u32 family; /* sa_family_t zero-extended */ + __be16 port; + __u8 pad[2]; + union { + __be32 v4_addr; + __u8 v6_addr[16]; + }; + } connect; }; }; diff --git a/io_uring/net.c b/io_uring/net.c index 30cd22c0b934..cceb5c1409ca 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1674,6 +1674,47 @@ void io_socket_bpf_populate(struct io_uring_bpf_ctx *bctx, struct io_kiocb *req) bctx->socket.protocol = sock->protocol; } +void io_connect_bpf_populate(struct io_uring_bpf_ctx *bctx, struct io_kiocb *req) +{ + struct io_connect *conn = io_kiocb_to_cmd(req, struct io_connect); + struct io_async_msghdr *iomsg = req->async_data; + struct sockaddr_storage *ss = &iomsg->addr; + + /* + * move_addr_to_kernel() skips the copy for addr_len == 0, so + * iomsg->addr may hold stale data from a prior CONNECT. Bail + * unless addr_len covers the family discriminator. + */ + if (conn->addr_len < (int)sizeof(sa_family_t)) + return; + + bctx->connect.family = ss->ss_family; + switch (ss->ss_family) { + case AF_INET: { + struct sockaddr_in *sin = (struct sockaddr_in *)ss; + + if (conn->addr_len < (int)sizeof(*sin)) + break; + bctx->connect.port = sin->sin_port; + bctx->connect.v4_addr = sin->sin_addr.s_addr; + break; + } + case AF_INET6: { + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)ss; + + if (conn->addr_len < (int)sizeof(*sin6)) + break; + bctx->connect.port = sin6->sin6_port; + memcpy(bctx->connect.v6_addr, &sin6->sin6_addr, + sizeof(bctx->connect.v6_addr)); + break; + } + default: + /* family is set; per-family fields stay zero - family-only filtering */ + break; + } +} + int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_socket *sock = io_kiocb_to_cmd(req, struct io_socket); diff --git a/io_uring/net.h b/io_uring/net.h index d4d1ddce50e3..51fda715d3c0 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -46,6 +46,7 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags); int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_socket(struct io_kiocb *req, unsigned int issue_flags); void io_socket_bpf_populate(struct io_uring_bpf_ctx *bctx, struct io_kiocb *req); +void io_connect_bpf_populate(struct io_uring_bpf_ctx *bctx, struct io_kiocb *req); int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_connect(struct io_kiocb *req, unsigned int issue_flags); @@ -69,4 +70,10 @@ static inline void io_socket_bpf_populate(struct io_uring_bpf_ctx *bctx, struct io_kiocb *req) { } + +static inline void io_connect_bpf_populate(struct io_uring_bpf_ctx *bctx, + struct io_kiocb *req) +{ +} + #endif diff --git a/io_uring/opdef.c b/io_uring/opdef.c index c3ef52b70811..8ea6bd274607 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -203,9 +203,11 @@ const struct io_issue_def io_issue_defs[] = { .unbound_nonreg_file = 1, .pollout = 1, #if defined(CONFIG_NET) + .filter_pdu_size = sizeof_field(struct io_uring_bpf_ctx, connect), .async_size = sizeof(struct io_async_msghdr), .prep = io_connect_prep, .issue = io_connect, + .filter_populate = io_connect_bpf_populate, #else .prep = io_eopnotsupp_prep, #endif -- cgit v1.3-14-g43fede From 45e57cfb7b10b64fb0d38d671d26ec935fc7efce Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 15 May 2026 11:35:12 -0400 Subject: fs: Clarify FS_CASEFOLD_FL semantics in UAPI header The existing one-liner "Folder is case insensitive" leaves the impression that FS_CASEFOLD_FL is reserved for directories. That impression is wrong: filesystems that derive case-insensitivity from mount or volume state report the bit on non-directory inodes via i_op->fileattr_get, so userspace inspecting FS_IOC_GETFLAGS can see it on any inode type. Replace the one-liner with a block comment that names directories as the typical case, records that non-directory inodes may also report the bit, and notes FS_XFLAG_CASEFOLD as the read-only companion exposed through FS_IOC_FSGETXATTR. Reported-by: sashiko-bot Closes: https://sashiko.dev/#/patchset/20260507-case-sensitivity-v14-0-e62cc8200435@oracle.com?part=3 Signed-off-by: Chuck Lever Link: https://patch.msgid.link/20260515153515.362266-5-cel@kernel.org Signed-off-by: Christian Brauner --- include/uapi/linux/fs.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 2ea4c81df08f..bd87262f2e34 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -395,7 +395,16 @@ struct file_attr { #define FS_DAX_FL 0x02000000 /* Inode is DAX */ #define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */ #define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ -#define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */ +/* + * FS_CASEFOLD_FL indicates case-insensitive name lookup. The + * bit is most often reported on directories, where it controls + * lookups of entries within. Filesystems that derive + * case-insensitivity from mount or volume state may also report + * it on non-directory inodes; userspace must not assume the bit + * is directory-only. FS_XFLAG_CASEFOLD reports the same + * information read-only via FS_IOC_FSGETXATTR. + */ +#define FS_CASEFOLD_FL 0x40000000 #define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ #define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ -- cgit v1.3-14-g43fede From 65efd1314dbcb37e4ab47974095ae97f90751f30 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 18 May 2026 16:40:32 +0200 Subject: media: include/uapi/linux/cec*.h: add CEC LIP support Add support for the new Latency Indication Protocol feature. This adds the opcodes and the wrapper functions. Signed-off-by: Hans Verkuil Link: https://patch.msgid.link/8dac7c99b7eab4fcc11d76d50dd08fb4448672f4.1779115235.git.hverkuil+cisco@kernel.org Signed-off-by: Mauro Carvalho Chehab Message-ID: <8dac7c99b7eab4fcc11d76d50dd08fb4448672f4.1779115235.git.hverkuil+cisco@kernel.org> --- include/uapi/linux/cec-funcs.h | 182 +++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/cec.h | 24 ++++++ 2 files changed, 206 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index 189ecf0e13cd..ba4b47de9bf0 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -1701,6 +1701,188 @@ static inline void cec_ops_request_current_latency(const struct cec_msg *msg, } +/* Latency Indication Protocol Feature */ +/* Only for CEC 2.0 and up */ +static inline void cec_msg_request_lip_support(struct cec_msg *msg, + int reply, __u16 phys_addr) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_REQUEST_LIP_SUPPORT; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_REPORT_LIP_SUPPORT : 0; +} + +static inline void cec_ops_request_lip_support(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_report_lip_support(struct cec_msg *msg, __u32 sqid) +{ + msg->len = 6; + msg->msg[1] = CEC_MSG_REPORT_LIP_SUPPORT; + msg->msg[2] = sqid >> 24; + msg->msg[3] = (sqid >> 16) & 0xff; + msg->msg[4] = (sqid >> 8) & 0xff; + msg->msg[5] = sqid & 0xff; +} + +static inline void cec_ops_report_lip_support(const struct cec_msg *msg, + __u32 *sqid) +{ + *sqid = (msg->msg[2] << 24) | (msg->msg[3] << 16) | + (msg->msg[4] << 8) | msg->msg[5]; +} + +static inline void cec_msg_request_audio_and_video_latency(struct cec_msg *msg, + int reply, __u8 video_format, + __u8 hdr_format, __u8 vrr_format, + __u8 audio_format, + __u8 audio_format_extension) +{ + msg->len = 6; + msg->msg[1] = CEC_MSG_REQUEST_AUDIO_AND_VIDEO_LATENCY; + msg->msg[2] = video_format; + msg->msg[3] = hdr_format; + msg->msg[4] = vrr_format; + msg->msg[5] = audio_format; + if (audio_format >= 1 && audio_format <= 31) { + msg->msg[6] = audio_format_extension; + msg->len++; + } + msg->reply = reply ? CEC_MSG_REPORT_AUDIO_AND_VIDEO_LATENCY : 0; +} + +static inline void cec_ops_request_audio_and_video_latency(const struct cec_msg *msg, + __u8 *video_format, + __u8 *hdr_format, + __u8 *vrr_format, + __u8 *audio_format, + __u8 *audio_format_extension) +{ + *video_format = msg->msg[2]; + *hdr_format = msg->msg[3]; + *vrr_format = msg->msg[4]; + *audio_format = msg->msg[5]; + *audio_format_extension = msg->len > 6 ? msg->msg[6] : 0; +} + +static inline void cec_msg_report_audio_and_video_latency(struct cec_msg *msg, + __u16 video_latency, + __u16 audio_latency) +{ + msg->len = 6; + msg->msg[1] = CEC_MSG_REPORT_AUDIO_AND_VIDEO_LATENCY; + msg->msg[2] = video_latency >> 8; + msg->msg[3] = video_latency & 0xff; + msg->msg[4] = audio_latency >> 8; + msg->msg[5] = audio_latency & 0xff; +} + +static inline void cec_ops_report_audio_and_video_latency(const struct cec_msg *msg, + __u16 *video_latency, + __u16 *audio_latency) +{ + *video_latency = (msg->msg[2] << 8) | msg->msg[3]; + *audio_latency = (msg->msg[4] << 8) | msg->msg[5]; +} + +static inline void cec_msg_request_audio_latency(struct cec_msg *msg, + int reply, + __u8 audio_format, + __u8 audio_format_extension) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_REQUEST_AUDIO_LATENCY; + msg->msg[2] = audio_format; + if (audio_format >= 1 && audio_format <= 31) { + msg->msg[3] = audio_format_extension; + msg->len++; + } + msg->reply = reply ? CEC_MSG_REPORT_AUDIO_LATENCY : 0; +} + +static inline void cec_ops_request_audio_latency(const struct cec_msg *msg, + __u8 *audio_format, + __u8 *audio_format_extension) +{ + *audio_format = msg->msg[2]; + *audio_format_extension = msg->len > 3 ? msg->msg[3] : 0; +} + +static inline void cec_msg_report_audio_latency(struct cec_msg *msg, + __u16 audio_latency) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_REPORT_AUDIO_LATENCY; + msg->msg[2] = audio_latency >> 8; + msg->msg[3] = audio_latency & 0xff; +} + +static inline void cec_ops_report_audio_latency(const struct cec_msg *msg, + __u16 *audio_latency) +{ + *audio_latency = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_request_video_latency(struct cec_msg *msg, + int reply, __u8 video_format, + __u8 hdr_format, + __u8 vrr_format) +{ + msg->len = 5; + msg->msg[1] = CEC_MSG_REQUEST_VIDEO_LATENCY; + msg->msg[2] = video_format; + msg->msg[3] = hdr_format; + msg->msg[4] = vrr_format; + msg->reply = reply ? CEC_MSG_REPORT_VIDEO_LATENCY : 0; +} + +static inline void cec_ops_request_video_latency(const struct cec_msg *msg, + __u8 *video_format, + __u8 *hdr_format, + __u8 *vrr_format) +{ + *video_format = msg->msg[2]; + *hdr_format = msg->msg[3]; + *vrr_format = msg->msg[4]; +} + +static inline void cec_msg_report_video_latency(struct cec_msg *msg, + __u16 video_latency) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_REPORT_VIDEO_LATENCY; + msg->msg[2] = video_latency >> 8; + msg->msg[3] = video_latency & 0xff; +} + +static inline void cec_ops_report_video_latency(const struct cec_msg *msg, + __u16 *video_latency) +{ + *video_latency = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_update_sqid(struct cec_msg *msg, __u32 sqid) +{ + msg->len = 6; + msg->msg[1] = CEC_MSG_UPDATE_SQID; + msg->msg[2] = sqid >> 24; + msg->msg[3] = (sqid >> 16) & 0xff; + msg->msg[4] = (sqid >> 8) & 0xff; + msg->msg[5] = sqid & 0xff; +} + +static inline void cec_ops_update_sqid(const struct cec_msg *msg, + __u32 *sqid) +{ + *sqid = (msg->msg[2] << 24) | (msg->msg[3] << 16) | + (msg->msg[4] << 8) | msg->msg[5]; +} + + /* Capability Discovery and Control Feature */ static inline void cec_msg_cdc_hec_inquire_state(struct cec_msg *msg, __u16 phys_addr1, diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index b2af1dddd4d7..75bc9e4e0350 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -1104,6 +1104,30 @@ struct cec_event { #define CEC_OP_AUD_OUT_COMPENSATED_PARTIAL_DELAY 3 +/* Latency Indication Protocol Feature */ +#define CEC_MSG_REQUEST_LIP_SUPPORT 0x50 +#define CEC_MSG_REPORT_LIP_SUPPORT 0x51 +#define CEC_MSG_REQUEST_AUDIO_AND_VIDEO_LATENCY 0x52 +/* HDR Format Operand (hdr_format) */ +#define CEC_OP_HDR_FORMAT_GAMMA_SDR 0 +#define CEC_OP_HDR_FORMAT_GAMMA_HDR 1 +#define CEC_OP_HDR_FORMAT_PQ 2 +#define CEC_OP_HDR_FORMAT_HLG 3 +#define CEC_OP_HDR_FORMAT_DYNAMIC_HDR_TYPE_1 8 +#define CEC_OP_HDR_FORMAT_DYNAMIC_HDR_TYPE_2 9 +#define CEC_OP_HDR_FORMAT_DYNAMIC_HDR_TYPE_4 11 +#define CEC_OP_HDR_FORMAT_DV_SINK_LED 16 +#define CEC_OP_HDR_FORMAT_DV_SOURCE_LED 17 +#define CEC_OP_HDR_FORMAT_HDR10PLUS 24 +#define CEC_OP_HDR_FORMAT_ETSI_TS_103_433 32 +#define CEC_MSG_REPORT_AUDIO_AND_VIDEO_LATENCY 0x53 +#define CEC_MSG_REQUEST_AUDIO_LATENCY 0x54 +#define CEC_MSG_REPORT_AUDIO_LATENCY 0x55 +#define CEC_MSG_REQUEST_VIDEO_LATENCY 0x56 +#define CEC_MSG_REPORT_VIDEO_LATENCY 0x57 +#define CEC_MSG_UPDATE_SQID 0x58 + + /* Capability Discovery and Control Feature */ #define CEC_MSG_CDC_MESSAGE 0xf8 /* Ethernet-over-HDMI: nobody ever does this... */ -- cgit v1.3-14-g43fede From 79500c929de313550554e604d22f3202955cea20 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 18 May 2026 16:40:35 +0200 Subject: media: include/uapi/linux/cec*: clarify which msgs are CEC 2.0 Drop comments about CEC 2.0 from cec-funcs.h. In cec.h clearly comment messages that are CEC 2.0 specific as such. Also rename references to HDMI 2.0 to CEC 2.0. The messages were marked as CEC 2.0 only. That is wrong, these messages are explicitly allowed for any CEC version. Signed-off-by: Hans Verkuil Link: https://patch.msgid.link/098789ee233f777d5ad87a72f09a997373c98d25.1779115235.git.hverkuil+cisco@kernel.org Signed-off-by: Mauro Carvalho Chehab Message-ID: <098789ee233f777d5ad87a72f09a997373c98d25.1779115235.git.hverkuil+cisco@kernel.org> --- include/uapi/linux/cec.h | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index 75bc9e4e0350..81a05c9c0706 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -742,7 +742,7 @@ struct cec_event { #define CEC_OP_PRIM_DEVTYPE_PROCESSOR 7 #define CEC_MSG_SET_MENU_LANGUAGE 0x32 -#define CEC_MSG_REPORT_FEATURES 0xa6 /* HDMI 2.0 */ +#define CEC_MSG_REPORT_FEATURES 0xa6 /* CEC 2.0 */ /* All Device Types Operand (all_device_types) */ #define CEC_OP_ALL_DEVTYPE_TV 0x80 #define CEC_OP_ALL_DEVTYPE_RECORD 0x40 @@ -777,7 +777,7 @@ struct cec_event { #define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX 0x02 #define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_VOLUME_LEVEL 0x01 -#define CEC_MSG_GIVE_FEATURES 0xa5 /* HDMI 2.0 */ +#define CEC_MSG_GIVE_FEATURES 0xa5 /* CEC 2.0 */ /* Deck Control Feature */ @@ -1067,7 +1067,7 @@ struct cec_event { #define CEC_OP_AUD_FMT_ID_CEA861 0 #define CEC_OP_AUD_FMT_ID_CEA861_CXT 1 -#define CEC_MSG_SET_AUDIO_VOLUME_LEVEL 0x73 +#define CEC_MSG_SET_AUDIO_VOLUME_LEVEL 0x73 /* CEC 2.0 */ /* Audio Rate Control Feature */ #define CEC_MSG_SET_AUDIO_RATE 0x9a @@ -1091,7 +1091,6 @@ struct cec_event { /* Dynamic Audio Lipsync Feature */ -/* Only for CEC 2.0 and up */ #define CEC_MSG_REQUEST_CURRENT_LATENCY 0xa7 #define CEC_MSG_REPORT_CURRENT_LATENCY 0xa8 /* Low Latency Mode Operand (low_latency_mode) */ @@ -1105,9 +1104,9 @@ struct cec_event { /* Latency Indication Protocol Feature */ -#define CEC_MSG_REQUEST_LIP_SUPPORT 0x50 -#define CEC_MSG_REPORT_LIP_SUPPORT 0x51 -#define CEC_MSG_REQUEST_AUDIO_AND_VIDEO_LATENCY 0x52 +#define CEC_MSG_REQUEST_LIP_SUPPORT 0x50 /* CEC 2.0 */ +#define CEC_MSG_REPORT_LIP_SUPPORT 0x51 /* CEC 2.0 */ +#define CEC_MSG_REQUEST_AUDIO_AND_VIDEO_LATENCY 0x52 /* CEC 2.0 */ /* HDR Format Operand (hdr_format) */ #define CEC_OP_HDR_FORMAT_GAMMA_SDR 0 #define CEC_OP_HDR_FORMAT_GAMMA_HDR 1 @@ -1120,12 +1119,12 @@ struct cec_event { #define CEC_OP_HDR_FORMAT_DV_SOURCE_LED 17 #define CEC_OP_HDR_FORMAT_HDR10PLUS 24 #define CEC_OP_HDR_FORMAT_ETSI_TS_103_433 32 -#define CEC_MSG_REPORT_AUDIO_AND_VIDEO_LATENCY 0x53 -#define CEC_MSG_REQUEST_AUDIO_LATENCY 0x54 -#define CEC_MSG_REPORT_AUDIO_LATENCY 0x55 -#define CEC_MSG_REQUEST_VIDEO_LATENCY 0x56 -#define CEC_MSG_REPORT_VIDEO_LATENCY 0x57 -#define CEC_MSG_UPDATE_SQID 0x58 +#define CEC_MSG_REPORT_AUDIO_AND_VIDEO_LATENCY 0x53 /* CEC 2.0 */ +#define CEC_MSG_REQUEST_AUDIO_LATENCY 0x54 /* CEC 2.0 */ +#define CEC_MSG_REPORT_AUDIO_LATENCY 0x55 /* CEC 2.0 */ +#define CEC_MSG_REQUEST_VIDEO_LATENCY 0x56 /* CEC 2.0 */ +#define CEC_MSG_REPORT_VIDEO_LATENCY 0x57 /* CEC 2.0 */ +#define CEC_MSG_UPDATE_SQID 0x58 /* CEC 2.0 */ /* Capability Discovery and Control Feature */ -- cgit v1.3-14-g43fede From 9bf93cb2e180a58d5984ba13daee95903ff4fc14 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Fri, 15 May 2026 13:50:28 +0000 Subject: pps: bump PPS device count Modern systems may have more than 16 PPS sources and current hard-coded limit breaks registration of some devices. Let's bump the limit to 256 in hope it will be enough in foreseen future. Signed-off-by: Vadim Fedorenko Acked-by: Rodolfo Giometti Link: https://patch.msgid.link/20260515135028.2021318-1-vadim.fedorenko@linux.dev Signed-off-by: Jakub Kicinski --- include/uapi/linux/pps.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pps.h b/include/uapi/linux/pps.h index 009ebcd8ced5..1088dea65e12 100644 --- a/include/uapi/linux/pps.h +++ b/include/uapi/linux/pps.h @@ -26,7 +26,7 @@ #include #define PPS_VERSION "5.3.6" -#define PPS_MAX_SOURCES 16 /* should be enough... */ +#define PPS_MAX_SOURCES 256 /* should be enough... */ /* Implementation note: the logical states ``assert'' and ``clear'' * are implemented in terms of the chip register, i.e. ``assert'' -- cgit v1.3-14-g43fede From c15d7a2a11ea055bcecc0b538ae8ba79475637f9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 4 Dec 2025 11:17:23 +0100 Subject: tee: fix tee_ioctl_object_invoke_arg padding The tee_ioctl_object_invoke_arg structure has padding on some architectures but not on x86-32 and a few others: include/linux/tee.h:474:32: error: padding struct to align 'params' [-Werror=padded] I expect that all current users of this are on architectures that do have implicit padding here (arm64, arm, x86, riscv), so make the padding explicit in order to avoid surprises if this later gets used elsewhere. Fixes: d5b8b0fa1775 ("tee: add TEE_IOCTL_PARAM_ATTR_TYPE_OBJREF") Signed-off-by: Arnd Bergmann Reviewed-by: Jens Wiklander Tested-by: Harshal Dev Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/uapi/linux/tee.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index cab5cadca8ef..5203977ed35d 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -470,6 +470,7 @@ struct tee_ioctl_object_invoke_arg { __u32 op; __u32 ret; __u32 num_params; + __u32 :32; /* num_params tells the actual number of element in params */ struct tee_ioctl_param params[]; }; -- cgit v1.3-14-g43fede From 7b5121c3374e24c8f6490b54f347eb06ee16028c Mon Sep 17 00:00:00 2001 From: Sergio Lopez Date: Tue, 28 Apr 2026 21:44:48 +0200 Subject: drm/virtio: support VIRTIO_GPU_F_BLOB_ALIGNMENT Support VIRTIO_GPU_F_BLOB_ALIGNMENT, a feature that indicates the device provides a valid blob_alignment field in its configuration, and that both RESOURCE_CREATE_BLOB and RESOURCE_MAP_BLOB requests must be aligned to that value. Signed-off-by: Sergio Lopez Signed-off-by: Dmitry Osipenko Link: https://patch.msgid.link/20260428194450.518296-2-slp@redhat.com --- drivers/gpu/drm/virtio/virtgpu_drv.c | 1 + drivers/gpu/drm/virtio/virtgpu_drv.h | 2 ++ drivers/gpu/drm/virtio/virtgpu_kms.c | 14 +++++++++++--- include/uapi/linux/virtio_gpu.h | 9 +++++++++ 4 files changed, 23 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index a5ce96fb8a1d..812ee3f5e4aa 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -163,6 +163,7 @@ static unsigned int features[] = { VIRTIO_GPU_F_RESOURCE_UUID, VIRTIO_GPU_F_RESOURCE_BLOB, VIRTIO_GPU_F_CONTEXT_INIT, + VIRTIO_GPU_F_BLOB_ALIGNMENT, }; static struct virtio_driver virtio_gpu_driver = { .feature_table = features, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 6f49213e23f8..04fe15d877cd 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -258,6 +258,7 @@ struct virtio_gpu_device { bool has_resource_blob; bool has_host_visible; bool has_context_init; + bool has_blob_alignment; struct virtio_shm_region host_visible_region; struct drm_mm host_visible_mm; @@ -271,6 +272,7 @@ struct virtio_gpu_device { uint32_t num_capsets; uint64_t capset_id_mask; struct list_head cap_cache; + uint32_t blob_alignment; /* protects uuid state when exporting */ spinlock_t resource_export_lock; diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 80ba69b4860b..cfde9f573df6 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -124,7 +124,7 @@ int virtio_gpu_init(struct virtio_device *vdev, struct drm_device *dev) struct virtio_gpu_device *vgdev; /* this will expand later */ struct virtqueue *vqs[2]; - u32 num_scanouts, num_capsets; + u32 num_scanouts, num_capsets, blob_alignment; int ret = 0; if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) @@ -198,14 +198,22 @@ int virtio_gpu_init(struct virtio_device *vdev, struct drm_device *dev) if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_CONTEXT_INIT)) vgdev->has_context_init = true; + if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_BLOB_ALIGNMENT)) { + vgdev->has_blob_alignment = true; + virtio_cread_le(vgdev->vdev, struct virtio_gpu_config, + blob_alignment, &blob_alignment); + vgdev->blob_alignment = blob_alignment; + } + DRM_INFO("features: %cvirgl %cedid %cresource_blob %chost_visible", vgdev->has_virgl_3d ? '+' : '-', vgdev->has_edid ? '+' : '-', vgdev->has_resource_blob ? '+' : '-', vgdev->has_host_visible ? '+' : '-'); - DRM_INFO("features: %ccontext_init\n", - vgdev->has_context_init ? '+' : '-'); + DRM_INFO("features: %ccontext_init %cblob_alignment\n", + vgdev->has_context_init ? '+' : '-', + vgdev->has_blob_alignment ? '+' : '-'); ret = virtio_find_vqs(vgdev->vdev, 2, vqs, vqs_info, NULL); if (ret) { diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index be109777d10d..4f530d90058c 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -64,6 +64,14 @@ * context_init and multiple timelines */ #define VIRTIO_GPU_F_CONTEXT_INIT 4 +/* + * The device provides a valid blob_alignment + * field in its configuration and both + * VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB and + * VIRTIO_GPU_CMD_RESOURCE_MAP_BLOB requests + * must be aligned to that value. + */ +#define VIRTIO_GPU_F_BLOB_ALIGNMENT 5 enum virtio_gpu_ctrl_type { VIRTIO_GPU_UNDEFINED = 0, @@ -365,6 +373,7 @@ struct virtio_gpu_config { __le32 events_clear; __le32 num_scanouts; __le32 num_capsets; + __le32 blob_alignment; }; /* simple formats for fbcon/X use */ -- cgit v1.3-14-g43fede From c4c01c4fd4a3916ffdfb35ad9f511c48e289f51c Mon Sep 17 00:00:00 2001 From: Niklas Söderlund Date: Fri, 1 May 2026 21:03:39 +0200 Subject: media: uapi: rkisp: Correct name version enum MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The name of the enum to hold the mapping of parameter buffer versions have a typo in the name, correct it. While this is a uAPI header the impact should be minimal as the enum is only used as a collection for the one version number supported. Fixes: e9d05e9d5db1 ("media: uapi: rkisp1-config: Add extensible params format") Cc: stable@vger.kernel.org Signed-off-by: Niklas Söderlund Reviewed-by: Laurent Pinchart Link: https://patch.msgid.link/20260501190339.3449193-1-niklas.soderlund+renesas@ragnatech.se Signed-off-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- include/uapi/linux/rkisp1-config.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index b2d2a71f7baf..7638b2220600 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -1535,11 +1535,11 @@ struct rkisp1_ext_params_wdr_config { sizeof(struct rkisp1_ext_params_wdr_config)) /** - * enum rksip1_ext_param_buffer_version - RkISP1 extensible parameters version + * enum rkisp1_ext_param_buffer_version - RkISP1 extensible parameters version * * @RKISP1_EXT_PARAM_BUFFER_V1: First version of RkISP1 extensible parameters */ -enum rksip1_ext_param_buffer_version { +enum rkisp1_ext_param_buffer_version { RKISP1_EXT_PARAM_BUFFER_V1 = V4L2_ISP_PARAMS_VERSION_V1, }; @@ -1601,7 +1601,7 @@ enum rksip1_ext_param_buffer_version { * +---------------------------------------------------------------------+ * * @version: The RkISP1 extensible parameters buffer version, see - * :c:type:`rksip1_ext_param_buffer_version` + * :c:type:`rkisp1_ext_param_buffer_version` * @data_size: The RkISP1 configuration data effective size, excluding this * header * @data: The RkISP1 extensible configuration data blocks -- cgit v1.3-14-g43fede From 27caa94f4d13d16f7f63eec879ea7d4d79699415 Mon Sep 17 00:00:00 2001 From: Barnabás PÅ‘cze Date: Mon, 11 May 2026 17:09:57 +0200 Subject: media: rkisp1: Add support for CAC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CAC block implements chromatic aberration correction. Expose it to userspace using the extensible parameters format. This was tested on the i.MX8MP platform, but based on available documentation it is also present in the RK3399 variant (V10). Thus presumably also in later versions, so no feature flag is introduced. Signed-off-by: Barnabás PÅ‘cze Reviewed-by: Jacopo Mondi Reviewed-by: Laurent Pinchart Link: https://patch.msgid.link/20260511150957.581049-1-barnabas.pocze@ideasonboard.com Signed-off-by: Laurent Pinchart Signed-off-by: Hans Verkuil --- .../media/platform/rockchip/rkisp1/rkisp1-params.c | 68 +++++++++++++ .../media/platform/rockchip/rkisp1/rkisp1-regs.h | 15 ++- include/uapi/linux/rkisp1-config.h | 107 ++++++++++++++++++++- 3 files changed, 187 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c index 6442436a5e42..042b759eba62 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c @@ -64,6 +64,7 @@ union rkisp1_ext_params_config { struct rkisp1_ext_params_compand_bls_config compand_bls; struct rkisp1_ext_params_compand_curve_config compand_curve; struct rkisp1_ext_params_wdr_config wdr; + struct rkisp1_ext_params_cac_config cac; }; enum rkisp1_params_formats { @@ -1413,6 +1414,47 @@ static void rkisp1_wdr_config(struct rkisp1_params *params, RKISP1_CIF_ISP_WDR_TONE_CURVE_YM_MASK); } +static void rkisp1_cac_config(struct rkisp1_params *params, + const struct rkisp1_cif_isp_cac_config *arg) +{ + u32 val; + + /* + * The enable bit is in the same register (RKISP1_CIF_ISP_CAC_CTRL), + * so only set the clipping mode, and do not modify the other bits. + */ + val = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_CAC_CTRL); + val &= ~(RKISP1_CIF_ISP_CAC_CTRL_H_CLIP_MODE | + RKISP1_CIF_ISP_CAC_CTRL_V_CLIP_MODE); + val |= FIELD_PREP(RKISP1_CIF_ISP_CAC_CTRL_H_CLIP_MODE, arg->h_clip_mode) | + FIELD_PREP(RKISP1_CIF_ISP_CAC_CTRL_V_CLIP_MODE, arg->v_clip_mode); + rkisp1_write(params->rkisp1, RKISP1_CIF_ISP_CAC_CTRL, val); + + val = FIELD_PREP(RKISP1_CIF_ISP_CAC_COUNT_START_H_MASK, arg->h_count_start) | + FIELD_PREP(RKISP1_CIF_ISP_CAC_COUNT_START_V_MASK, arg->v_count_start); + rkisp1_write(params->rkisp1, RKISP1_CIF_ISP_CAC_COUNT_START, val); + + val = FIELD_PREP(RKISP1_CIF_ISP_CAC_RED_MASK, arg->red[0]) | + FIELD_PREP(RKISP1_CIF_ISP_CAC_BLUE_MASK, arg->blue[0]); + rkisp1_write(params->rkisp1, RKISP1_CIF_ISP_CAC_A, val); + + val = FIELD_PREP(RKISP1_CIF_ISP_CAC_RED_MASK, arg->red[1]) | + FIELD_PREP(RKISP1_CIF_ISP_CAC_BLUE_MASK, arg->blue[1]); + rkisp1_write(params->rkisp1, RKISP1_CIF_ISP_CAC_B, val); + + val = FIELD_PREP(RKISP1_CIF_ISP_CAC_RED_MASK, arg->red[2]) | + FIELD_PREP(RKISP1_CIF_ISP_CAC_BLUE_MASK, arg->blue[2]); + rkisp1_write(params->rkisp1, RKISP1_CIF_ISP_CAC_C, val); + + val = FIELD_PREP(RKISP1_CIF_ISP_CAC_NF_MASK, arg->x_nf) | + FIELD_PREP(RKISP1_CIF_ISP_CAC_NS_MASK, arg->x_ns); + rkisp1_write(params->rkisp1, RKISP1_CIF_ISP_CAC_X_NORM, val); + + val = FIELD_PREP(RKISP1_CIF_ISP_CAC_NF_MASK, arg->y_nf) | + FIELD_PREP(RKISP1_CIF_ISP_CAC_NS_MASK, arg->y_ns); + rkisp1_write(params->rkisp1, RKISP1_CIF_ISP_CAC_Y_NORM, val); +} + static void rkisp1_isp_isr_other_config(struct rkisp1_params *params, const struct rkisp1_params_cfg *new_params) @@ -2089,6 +2131,25 @@ static void rkisp1_ext_params_wdr(struct rkisp1_params *params, RKISP1_CIF_ISP_WDR_CTRL_ENABLE); } +static void rkisp1_ext_params_cac(struct rkisp1_params *params, + const union rkisp1_ext_params_config *block) +{ + const struct rkisp1_ext_params_cac_config *cac = &block->cac; + + if (cac->header.flags & RKISP1_EXT_PARAMS_FL_BLOCK_DISABLE) { + rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_CAC_CTRL, + RKISP1_CIF_ISP_CAC_CTRL_ENABLE); + return; + } + + rkisp1_cac_config(params, &cac->config); + + if ((cac->header.flags & RKISP1_EXT_PARAMS_FL_BLOCK_ENABLE) && + !(params->enabled_blocks & BIT(cac->header.type))) + rkisp1_param_set_bits(params, RKISP1_CIF_ISP_CAC_CTRL, + RKISP1_CIF_ISP_CAC_CTRL_ENABLE); +} + typedef void (*rkisp1_block_handler)(struct rkisp1_params *params, const union rkisp1_ext_params_config *config); @@ -2185,6 +2246,10 @@ static const struct rkisp1_ext_params_handler { .handler = rkisp1_ext_params_wdr, .group = RKISP1_EXT_PARAMS_BLOCK_GROUP_OTHERS, }, + [RKISP1_EXT_PARAMS_BLOCK_TYPE_CAC] = { + .handler = rkisp1_ext_params_cac, + .group = RKISP1_EXT_PARAMS_BLOCK_GROUP_OTHERS, + }, }; #define RKISP1_PARAMS_BLOCK_INFO(block, data) \ @@ -2215,6 +2280,7 @@ rkisp1_ext_params_block_types_info[] = { RKISP1_PARAMS_BLOCK_INFO(COMPAND_EXPAND, compand_curve), RKISP1_PARAMS_BLOCK_INFO(COMPAND_COMPRESS, compand_curve), RKISP1_PARAMS_BLOCK_INFO(WDR, wdr), + RKISP1_PARAMS_BLOCK_INFO(CAC, cac), }; static_assert(ARRAY_SIZE(rkisp1_ext_params_handlers) == @@ -2474,6 +2540,8 @@ void rkisp1_params_disable(struct rkisp1_params *params) rkisp1_ie_enable(params, false); rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_DPF_MODE, RKISP1_CIF_ISP_DPF_MODE_EN); + rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_CAC_CTRL, + RKISP1_CIF_ISP_CAC_CTRL_ENABLE); } static const struct rkisp1_params_ops rkisp1_v10_params_ops = { diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h index fbeb186cde0d..2b842194de8f 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h @@ -724,6 +724,17 @@ #define RKISP1_CIF_ISP_WDR_DMIN_STRENGTH_MASK GENMASK(20, 16) #define RKISP1_CIF_ISP_WDR_DMIN_STRENGTH_MAX 16U +/* CAC */ +#define RKISP1_CIF_ISP_CAC_CTRL_ENABLE BIT(0) +#define RKISP1_CIF_ISP_CAC_CTRL_V_CLIP_MODE GENMASK(2, 1) +#define RKISP1_CIF_ISP_CAC_CTRL_H_CLIP_MODE BIT(3) +#define RKISP1_CIF_ISP_CAC_COUNT_START_H_MASK GENMASK(12, 0) +#define RKISP1_CIF_ISP_CAC_COUNT_START_V_MASK GENMASK(28, 16) +#define RKISP1_CIF_ISP_CAC_RED_MASK GENMASK(8, 0) +#define RKISP1_CIF_ISP_CAC_BLUE_MASK GENMASK(24, 16) +#define RKISP1_CIF_ISP_CAC_NF_MASK GENMASK(4, 0) +#define RKISP1_CIF_ISP_CAC_NS_MASK GENMASK(19, 16) + /* =================================================================== */ /* CIF Registers */ /* =================================================================== */ @@ -1196,8 +1207,8 @@ #define RKISP1_CIF_ISP_CAC_A (RKISP1_CIF_ISP_CAC_BASE + 0x00000008) #define RKISP1_CIF_ISP_CAC_B (RKISP1_CIF_ISP_CAC_BASE + 0x0000000c) #define RKISP1_CIF_ISP_CAC_C (RKISP1_CIF_ISP_CAC_BASE + 0x00000010) -#define RKISP1_CIF_ISP_X_NORM (RKISP1_CIF_ISP_CAC_BASE + 0x00000014) -#define RKISP1_CIF_ISP_Y_NORM (RKISP1_CIF_ISP_CAC_BASE + 0x00000018) +#define RKISP1_CIF_ISP_CAC_X_NORM (RKISP1_CIF_ISP_CAC_BASE + 0x00000014) +#define RKISP1_CIF_ISP_CAC_Y_NORM (RKISP1_CIF_ISP_CAC_BASE + 0x00000018) #define RKISP1_CIF_ISP_EXP_BASE 0x00002600 #define RKISP1_CIF_ISP_EXP_CTRL (RKISP1_CIF_ISP_EXP_BASE + 0x00000000) diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 7638b2220600..d97384abc157 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -967,6 +967,92 @@ struct rkisp1_cif_isp_wdr_config { __u8 use_iref; }; +/* + * enum rkisp1_cif_isp_cac_h_clip_mode - horizontal clipping mode + * + * @RKISP1_CIF_ISP_CAC_H_CLIP_MODE_4PX: +/- 4 pixels + * @RKISP1_CIF_ISP_CAC_H_CLIP_MODE_4_5PX: +/- 4/5 pixels depending on bayer position + */ +enum rkisp1_cif_isp_cac_h_clip_mode { + RKISP1_CIF_ISP_CAC_H_CLIP_MODE_4PX = 0, + RKISP1_CIF_ISP_CAC_H_CLIP_MODE_4_5PX = 1, +}; + +/** + * enum rkisp1_cif_isp_cac_v_clip_mode - vertical clipping mode + * + * @RKISP1_CIF_ISP_CAC_V_CLIP_MODE_2PX: +/- 2 pixels + * @RKISP1_CIF_ISP_CAC_V_CLIP_MODE_3PX: +/- 3 pixels + * @RKISP1_CIF_ISP_CAC_V_CLIP_MODE_3_4PX: +/- 3/4 pixels depending on bayer position + */ +enum rkisp1_cif_isp_cac_v_clip_mode { + RKISP1_CIF_ISP_CAC_V_CLIP_MODE_2PX = 0, + RKISP1_CIF_ISP_CAC_V_CLIP_MODE_3PX = 1, + RKISP1_CIF_ISP_CAC_V_CLIP_MODE_3_4PX = 2, +}; + +/** + * struct rkisp1_cif_isp_cac_config - chromatic aberration correction configuration + * + * The correction is carried out by shifting the red and blue pixels relative + * to the green ones, depending on the distance from the optical center: + * + * @h_count_start: horizontal coordinate of the optical center (13-bit unsigned integer; [1,8191]) + * @v_count_start: vertical coordinate of the optical center (13-bit unsigned integer; [1,8191]) + * + * For each pixel, the x/y distances from the optical center are calculated and + * then transformed into the [0,255] range based on the following formula: + * + * (((d << 4) >> ns) * nf) >> 5 + * + * where `d` is the distance, `ns` and `nf` are the normalization parameters: + * + * @x_nf: horizontal normalization scale parameter (5-bit unsigned integer; [0,31]) + * @x_ns: horizontal normalization shift parameter (4-bit unsigned integer; [0,15]) + * + * @y_nf: vertical normalization scale parameter (5-bit unsigned integer; [0,31]) + * @y_ns: vertical normalization shift parameter (4-bit unsigned integer; [0,15]) + * + * These parameters should be chosen based on the image resolution, the position + * of the optical center, and the shape of pixels, so that no normalized distance + * is larger than 255. If the pixels have square shape, the two sets of parameters + * should be equal. + * + * The actual amount of correction is calculated with a third degree polynomial: + * + * c[0] * r + c[1] * r^2 + c[2] * r^3 + * + * where `c` is the set of coefficients for the given color, and `r` is distance: + * + * @red: red coefficients (5.4 two's complement; [-16,15.9375]) + * @blue: blue coefficients (5.4 two's complement; [-16,15.9375]) + * + * Finally, the amount is clipped as requested: + * + * @h_clip_mode: maximum horizontal shift (from enum rkisp1_cif_isp_cac_h_clip_mode) + * @v_clip_mode: maximum vertical shift (from enum rkisp1_cif_isp_cac_v_clip_mode) + * + * A positive result will shift away from the optical center, while a negative + * one will shift towards the optical center. In the latter case, the pixel + * values at the edges are duplicated. + */ +struct rkisp1_cif_isp_cac_config { + __u8 h_clip_mode; + __u8 v_clip_mode; + + __u16 h_count_start; + __u16 v_count_start; + + __u16 red[3]; + __u16 blue[3]; + + __u8 x_nf; + __u8 x_ns; + + __u8 y_nf; + __u8 y_ns; +}; + /*---------- PART2: Measurement Statistics ------------*/ /** @@ -1138,6 +1224,7 @@ struct rkisp1_stat_buffer { * @RKISP1_EXT_PARAMS_BLOCK_TYPE_COMPAND_EXPAND: Companding expand curve * @RKISP1_EXT_PARAMS_BLOCK_TYPE_COMPAND_COMPRESS: Companding compress curve * @RKISP1_EXT_PARAMS_BLOCK_TYPE_WDR: Wide dynamic range + * @RKISP1_EXT_PARAMS_BLOCK_TYPE_CAC: Chromatic aberration correction */ enum rkisp1_ext_params_block_type { RKISP1_EXT_PARAMS_BLOCK_TYPE_BLS, @@ -1161,6 +1248,7 @@ enum rkisp1_ext_params_block_type { RKISP1_EXT_PARAMS_BLOCK_TYPE_COMPAND_EXPAND, RKISP1_EXT_PARAMS_BLOCK_TYPE_COMPAND_COMPRESS, RKISP1_EXT_PARAMS_BLOCK_TYPE_WDR, + RKISP1_EXT_PARAMS_BLOCK_TYPE_CAC, }; /* For backward compatibility */ @@ -1507,6 +1595,22 @@ struct rkisp1_ext_params_wdr_config { struct rkisp1_cif_isp_wdr_config config; } __attribute__((aligned(8))); +/** + * struct rkisp1_ext_params_cac_config - RkISP1 extensible params CAC config + * + * RkISP1 extensible parameters CAC block. + * Identified by :c:type:`RKISP1_EXT_PARAMS_BLOCK_TYPE_CAC`. + * + * @header: The RkISP1 extensible parameters header, see + * :c:type:`rkisp1_ext_params_block_header` + * @config: CAC configuration, see + * :c:type:`rkisp1_cif_isp_cac_config` + */ +struct rkisp1_ext_params_cac_config { + struct rkisp1_ext_params_block_header header; + struct rkisp1_cif_isp_cac_config config; +} __attribute__((aligned(8))); + /* * The rkisp1_ext_params_compand_curve_config structure is counted twice as it * is used for both the COMPAND_EXPAND and COMPAND_COMPRESS block types. @@ -1532,7 +1636,8 @@ struct rkisp1_ext_params_wdr_config { sizeof(struct rkisp1_ext_params_compand_bls_config) +\ sizeof(struct rkisp1_ext_params_compand_curve_config) +\ sizeof(struct rkisp1_ext_params_compand_curve_config) +\ - sizeof(struct rkisp1_ext_params_wdr_config)) + sizeof(struct rkisp1_ext_params_wdr_config) +\ + sizeof(struct rkisp1_ext_params_cac_config)) /** * enum rkisp1_ext_param_buffer_version - RkISP1 extensible parameters version -- cgit v1.3-14-g43fede From 0850005c26d2623f3d77489cf27d342191a97b5c Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 18 May 2026 16:25:00 +0800 Subject: net: dsa: add NETC switch tag support The NXP NETC switch tag is a proprietary header added to frames after the source MAC address. The switch tag has 3 types, and each type has 1 ~ 4 subtypes, the details are as follows. Forward NXP switch tag (Type=0): Represents forwarded frames. - SubType = 0 - Normal frame processing. To_Port NXP switch tag (Type=1): Represents frames that are to be sent to a specific switch port. - SubType = 0. No request to perform timestamping. - SubType = 1. Request to perform one-step timestamping. - SubType = 2. Request to perform two-step timestamping. - SubType = 3. Request to perform both one-step timestamping and two-step timestamping. To_Host NXP switch tag (Type=2): Represents frames redirected or copied to the switch management port. - SubType = 0. Received frames redirected or copied to the switch management port. - SubType = 1. Received frames redirected or copied to the switch management port with captured timestamp at the switch port where the frame was received. - SubType = 2. Transmit timestamp response (two-step timestamping). In addition, the length of different type switch tag is different, the minimum length is 6 bytes, the maximum length is 14 bytes. Currently, Forward tag, SubType 0 of To_Port tag and Subtype 0 of To_Host tag are supported. More tags will be supported in the future. Signed-off-by: Wei Fang Link: https://patch.msgid.link/20260518082506.1318236-10-wei.fang@nxp.com Signed-off-by: Paolo Abeni --- include/linux/dsa/tag_netc.h | 14 +++ include/net/dsa.h | 2 + include/uapi/linux/if_ether.h | 1 + net/dsa/Kconfig | 10 ++ net/dsa/Makefile | 1 + net/dsa/tag_netc.c | 214 ++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 242 insertions(+) create mode 100644 include/linux/dsa/tag_netc.h create mode 100644 net/dsa/tag_netc.c (limited to 'include/uapi/linux') diff --git a/include/linux/dsa/tag_netc.h b/include/linux/dsa/tag_netc.h new file mode 100644 index 000000000000..fe964722e5b0 --- /dev/null +++ b/include/linux/dsa/tag_netc.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2025-2026 NXP + */ + +#ifndef __NET_DSA_TAG_NETC_H +#define __NET_DSA_TAG_NETC_H + +#include +#include + +#define NETC_TAG_MAX_LEN 14 + +#endif diff --git a/include/net/dsa.h b/include/net/dsa.h index 4cc67469cf2e..8c16ef23cc10 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -58,6 +58,7 @@ struct tc_action; #define DSA_TAG_PROTO_YT921X_VALUE 30 #define DSA_TAG_PROTO_MXL_GSW1XX_VALUE 31 #define DSA_TAG_PROTO_MXL862_VALUE 32 +#define DSA_TAG_PROTO_NETC_VALUE 33 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -93,6 +94,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_YT921X = DSA_TAG_PROTO_YT921X_VALUE, DSA_TAG_PROTO_MXL_GSW1XX = DSA_TAG_PROTO_MXL_GSW1XX_VALUE, DSA_TAG_PROTO_MXL862 = DSA_TAG_PROTO_MXL862_VALUE, + DSA_TAG_PROTO_NETC = DSA_TAG_PROTO_NETC_VALUE, }; struct dsa_switch; diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index df9d44a11540..fb5efc8e06cc 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -123,6 +123,7 @@ #define ETH_P_DSA_A5PSW 0xE001 /* A5PSW Tag Value [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_NXP_NETC 0xFD3A /* NXP NETC DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is more than this value * then the frame is Ethernet II. Else it is 802.3 */ diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 5ed8c704636d..d5e725b90d78 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -125,6 +125,16 @@ config NET_DSA_TAG_KSZ Say Y if you want to enable support for tagging frames for the Microchip 8795/937x/9477/9893 families of switches. +config NET_DSA_TAG_NETC + tristate "Tag driver for NXP NETC switches" + help + Say Y or M if you want to enable support for the NXP Switch Tag (NST), + as implemented by NXP NETC switches having version 4.3 or later. The + switch tag is a proprietary header added to frames after the source + MAC address, it has 3 types and each type has different subtypes, so + its length depends on the type and subtype of the tag, the maximum + length is 14 bytes. + config NET_DSA_TAG_OCELOT tristate "Tag driver for Ocelot family of switches, using NPI port" select PACKING diff --git a/net/dsa/Makefile b/net/dsa/Makefile index bf7247759a64..b8c2667cd14a 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o obj-$(CONFIG_NET_DSA_TAG_MXL_862XX) += tag_mxl862xx.o obj-$(CONFIG_NET_DSA_TAG_MXL_GSW1XX) += tag_mxl-gsw1xx.o +obj-$(CONFIG_NET_DSA_TAG_NETC) += tag_netc.o obj-$(CONFIG_NET_DSA_TAG_NONE) += tag_none.o obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o diff --git a/net/dsa/tag_netc.c b/net/dsa/tag_netc.c new file mode 100644 index 000000000000..ccedfe3a80b6 --- /dev/null +++ b/net/dsa/tag_netc.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2025-2026 NXP + */ + +#include + +#include "tag.h" + +#define NETC_NAME "nxp_netc" + +/* Forward NXP switch tag */ +#define NETC_TAG_FORWARD 0 + +/* To_Port NXP switch tag */ +#define NETC_TAG_TO_PORT 1 +/* SubType0: No request to perform timestamping */ +#define NETC_TAG_TP_SUBTYPE0 0 + +/* To_Host NXP switch tag */ +#define NETC_TAG_TO_HOST 2 +/* SubType0: frames redirected or copied to CPU port */ +#define NETC_TAG_TH_SUBTYPE0 0 +/* SubType1: frames redirected or copied to CPU port with timestamp */ +#define NETC_TAG_TH_SUBTYPE1 1 +/* SubType2: Transmit timestamp response (two-step timestamping) */ +#define NETC_TAG_TH_SUBTYPE2 2 + +/* NETC switch tag lengths */ +#define NETC_TAG_FORWARD_LEN 6 +#define NETC_TAG_TP_SUBTYPE0_LEN 6 +#define NETC_TAG_TH_SUBTYPE0_LEN 6 +#define NETC_TAG_TH_SUBTYPE1_LEN 14 +#define NETC_TAG_TH_SUBTYPE2_LEN 14 +#define NETC_TAG_CMN_LEN 5 + +#define NETC_TAG_SUBTYPE GENMASK(3, 0) +#define NETC_TAG_TYPE GENMASK(7, 4) +#define NETC_TAG_QV BIT(0) +#define NETC_TAG_IPV GENMASK(4, 2) +#define NETC_TAG_SWITCH GENMASK(2, 0) +#define NETC_TAG_PORT GENMASK(7, 3) + +struct netc_tag_cmn { + __be16 tpid; + u8 type; + u8 qos; + u8 switch_port; +} __packed; + +static void netc_fill_common_tag(struct netc_tag_cmn *tag, u8 type, + u8 subtype, u8 sw_id, u8 port, u8 ipv) +{ + tag->tpid = htons(ETH_P_NXP_NETC); + tag->type = FIELD_PREP(NETC_TAG_TYPE, type) | + FIELD_PREP(NETC_TAG_SUBTYPE, subtype); + tag->qos = NETC_TAG_QV | FIELD_PREP(NETC_TAG_IPV, ipv); + tag->switch_port = FIELD_PREP(NETC_TAG_SWITCH, sw_id) | + FIELD_PREP(NETC_TAG_PORT, port); +} + +static void *netc_fill_common_tp_tag(struct sk_buff *skb, + struct net_device *ndev, + u8 subtype, int tag_len) +{ + struct dsa_port *dp = dsa_user_to_port(ndev); + u16 queue = skb_get_queue_mapping(skb); + s8 ipv = netdev_txq_to_tc(ndev, queue); + void *tag; + + if (unlikely(ipv < 0)) + ipv = 0; + + skb_push(skb, tag_len); + dsa_alloc_etype_header(skb, tag_len); + + tag = dsa_etype_header_pos_tx(skb); + memset(tag + NETC_TAG_CMN_LEN, 0, tag_len - NETC_TAG_CMN_LEN); + /* As 'dsa,member' is a required property for NETC switch, the member + * is used to specify the switch ID (thus the hardware switch ID and + * the software switch ID are consistent), its range is 1 ~ 7. The + * NETC switch driver will check this value, and if it is invalid, + * the switch driver will fail the probe. + * In addition, according to the nxp,netc-switch.yaml doc, the port + * index will not be greater than 0xf. + */ + netc_fill_common_tag(tag, NETC_TAG_TO_PORT, subtype, + dp->ds->index, dp->index, ipv); + + return tag; +} + +static void netc_fill_tp_tag_subtype0(struct sk_buff *skb, + struct net_device *ndev) +{ + netc_fill_common_tp_tag(skb, ndev, NETC_TAG_TP_SUBTYPE0, + NETC_TAG_TP_SUBTYPE0_LEN); +} + +/* Currently only support To_Port tag, subtype 0 */ +static struct sk_buff *netc_xmit(struct sk_buff *skb, + struct net_device *ndev) +{ + netc_fill_tp_tag_subtype0(skb, ndev); + + return skb; +} + +static int netc_get_rx_tag_len(int type, int subtype) +{ + /* Only NETC_TAG_TO_HOST and NETC_TAG_FORWARD are expected in RX, + * NETC_TAG_TO_PORT is a TX switch tag that does not exist in RX. + */ + if (type == NETC_TAG_TO_HOST) { + if (subtype == NETC_TAG_TH_SUBTYPE1) + return NETC_TAG_TH_SUBTYPE1_LEN; + else if (subtype == NETC_TAG_TH_SUBTYPE2) + return NETC_TAG_TH_SUBTYPE2_LEN; + else + return NETC_TAG_TH_SUBTYPE0_LEN; + } + + return NETC_TAG_FORWARD_LEN; +} + +static struct sk_buff *netc_rcv(struct sk_buff *skb, + struct net_device *ndev) +{ + struct netc_tag_cmn *tag_cmn; + int tag_len, sw_id, port; + int type, subtype; + + if (unlikely(!pskb_may_pull(skb, NETC_TAG_MAX_LEN))) + return NULL; + + tag_cmn = dsa_etype_header_pos_rx(skb); + if (ntohs(tag_cmn->tpid) != ETH_P_NXP_NETC) { + dev_warn_ratelimited(&ndev->dev, "Unknown TPID 0x%04x\n", + ntohs(tag_cmn->tpid)); + + return NULL; + } + + if (tag_cmn->qos & NETC_TAG_QV) + skb->priority = FIELD_GET(NETC_TAG_IPV, tag_cmn->qos); + + sw_id = FIELD_GET(NETC_TAG_SWITCH, tag_cmn->switch_port); + /* ENETC VEPA switch ID (0) is not supported yet */ + if (!sw_id) { + dev_warn_ratelimited(&ndev->dev, + "VEPA switch ID is not supported yet\n"); + + return NULL; + } + + port = FIELD_GET(NETC_TAG_PORT, tag_cmn->switch_port); + skb->dev = dsa_conduit_find_user(ndev, sw_id, port); + if (!skb->dev) + return NULL; + + type = FIELD_GET(NETC_TAG_TYPE, tag_cmn->type); + subtype = FIELD_GET(NETC_TAG_SUBTYPE, tag_cmn->type); + if (type == NETC_TAG_FORWARD) { + dsa_default_offload_fwd_mark(skb); + } else if (type == NETC_TAG_TO_HOST) { + /* Currently only subtype0 supported */ + if (subtype != NETC_TAG_TH_SUBTYPE0) + return NULL; + } else { + dev_warn_ratelimited(&ndev->dev, + "Unexpected tag type %d\n", type); + return NULL; + } + + /* Remove Switch tag from the frame */ + tag_len = netc_get_rx_tag_len(type, subtype); + skb_pull_rcsum(skb, tag_len); + dsa_strip_etype_header(skb, tag_len); + + return skb; +} + +static void netc_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + struct netc_tag_cmn *tag_cmn = (struct netc_tag_cmn *)(skb->data - 2); + int subtype = FIELD_GET(NETC_TAG_SUBTYPE, tag_cmn->type); + int type = FIELD_GET(NETC_TAG_TYPE, tag_cmn->type); + int tag_len = netc_get_rx_tag_len(type, subtype); + + /* The RX minimum frame length of the NETC switch port is 64 bytes, + * and the frame is received by the ENETC driver. From the hardware + * perspective, the receive buffer of RX BD is at least 128 bytes, + * so the switch tag header is guaranteed to be in the linear region + * of the skb. + */ + *offset = tag_len; + *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; +} + +static const struct dsa_device_ops netc_netdev_ops = { + .name = NETC_NAME, + .proto = DSA_TAG_PROTO_NETC, + .xmit = netc_xmit, + .rcv = netc_rcv, + .needed_headroom = NETC_TAG_MAX_LEN, + .flow_dissect = netc_flow_dissect, +}; + +MODULE_DESCRIPTION("DSA tag driver for NXP NETC switch family"); +MODULE_LICENSE("GPL"); + +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_NETC, NETC_NAME); +module_dsa_tag_driver(netc_netdev_ops); -- cgit v1.3-14-g43fede From 8b82cacad92ebae9619872a5a69c570eba30140b Mon Sep 17 00:00:00 2001 From: Dorjoy Chowdhury Date: Sat, 16 May 2026 16:42:39 +0200 Subject: openat2: new OPENAT2_REGULAR flag support This flag indicates the path should be opened if it's a regular file. This is useful to write secure programs that want to avoid being tricked into opening device nodes with special semantics while thinking they operate on regular files. This is a requested feature from the uapi-group[1]. The previously introduced EFTYPE error code is returned when the path doesn't refer to a regular file. For example, if openat2 is called on path /dev/null with OPENAT2_REGULAR in the flag param, it will return -EFTYPE. When used in combination with O_CREAT, either the regular file is created, or if the path already exists, it is opened if it's a regular file. Otherwise, -EFTYPE is returned. When OPENAT2_REGULAR is combined with O_DIRECTORY, -EINVAL is returned as it doesn't make sense to open a path that is both a directory and a regular file. The UAPI bit lives in the upper 32 bits of open_how::flags (((__u64)1 << 32)) so that open(2) and openat(2) -- whose @flags argument is a C int -- cannot physically express it. This is a structural guarantee, not a runtime mask: the bit is unrepresentable in 32 bits. Because the rest of the VFS open path narrows to 32 bits in several places (op->open_flag, f->f_flags, the unsigned open_flag argument of i_op->atomic_open()), build_open_flags() translates OPENAT2_REGULAR into a kernel-internal lower-32-bit carrier __O_REGULAR (bit 4, unused as an O_* on every architecture) before the assignment to op->open_flag. __O_REGULAR then rides through the existing channels exactly like __FMODE_EXEC. do_dentry_open() strips it so it cannot leak back to userspace via fcntl(F_GETFL). Four BUILD_BUG_ON_MSG() invariants in build_open_flags() prevent any future bit collision or accidental low-32 redefinition: - VALID_OPEN_FLAGS fits in 32 bits. - OPENAT2_REGULAR lives in the upper 32 bits. - OPENAT2_REGULAR does not alias any open()/openat() flag. - __O_REGULAR does not alias any user-visible flag. [1]: https://uapi-group.org/kernel-features/#ability-to-only-open-regular-files Christian Brauner says: Move OPENAT2_REGULAR to the upper 32 bits of open_how::flags with a kernel-internal __O_REGULAR carrier so that open(2)/openat(2) cannot encode the flag; add BUILD_BUG_ON_MSG() invariants and register __O_REGULAR in the fcntl_init() allocation-uniqueness BUILD_BUG_ON() (bit count 21 -> 22). Signed-off-by: Dorjoy Chowdhury Link: https://patch.msgid.link/20260328172314.45807-2-dorjoychy111@gmail.com Reviewed-by: Jeff Layton Reviewed-by: Aleksa Sarai Signed-off-by: Christian Brauner (Amutable) --- fs/ceph/file.c | 4 ++++ fs/fcntl.c | 4 ++-- fs/gfs2/inode.c | 7 +++++++ fs/namei.c | 4 ++++ fs/nfs/dir.c | 4 ++++ fs/open.c | 35 ++++++++++++++++++++++++++++++++--- fs/smb/client/dir.c | 18 +++++++++++++++--- include/linux/fcntl.h | 18 ++++++++++++++++++ include/uapi/linux/openat2.h | 7 +++++++ 9 files changed, 93 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d54d71669176..0ad42e1cc305 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -996,6 +996,10 @@ retry: ceph_init_inode_acls(newino, &as_ctx); file->f_mode |= FMODE_CREATED; } + if ((flags & __O_REGULAR) && !d_is_reg(dentry)) { + err = -EFTYPE; + goto out_req; + } err = finish_open(file, dentry, ceph_open); } out_req: diff --git a/fs/fcntl.c b/fs/fcntl.c index 7d2165855a9c..b3ea135b74d8 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -1169,10 +1169,10 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != + BUILD_BUG_ON(22 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | - __FMODE_EXEC)); + __FMODE_EXEC | __O_REGULAR)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index e9bf4879c07f..e9895dea0da4 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -738,6 +738,13 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, inode = gfs2_dir_search(dir, &dentry->d_name, !S_ISREG(mode) || excl); error = PTR_ERR(inode); if (!IS_ERR(inode)) { + if (file && (file->f_flags & __O_REGULAR) && + !S_ISREG(inode->i_mode)) { + iput(inode); + inode = NULL; + error = -EFTYPE; + goto fail_gunlock; + } if (S_ISDIR(inode->i_mode)) { iput(inode); inode = NULL; diff --git a/fs/namei.c b/fs/namei.c index c7fac83c9a85..e1fe0f28b923 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4679,6 +4679,10 @@ static int do_open(struct nameidata *nd, if (unlikely(error)) return error; } + + if ((open_flag & __O_REGULAR) && !d_is_reg(nd->path.dentry)) + return -EFTYPE; + if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) return -ENOTDIR; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e9ce1883288c..1b9c368fb133 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2194,6 +2194,10 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, break; case -EISDIR: case -ENOTDIR: + if (open_flags & __O_REGULAR) { + err = -EFTYPE; + break; + } goto no_open; case -ELOOP: if (!(open_flags & O_NOFOLLOW)) diff --git a/fs/open.c b/fs/open.c index 9e0164a8c1fb..5458668a68e1 100644 --- a/fs/open.c +++ b/fs/open.c @@ -960,7 +960,7 @@ static int do_dentry_open(struct file *f, if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO) f->f_mode |= FMODE_CAN_ODIRECT; - f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); + f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | __O_REGULAR); f->f_iocb_flags = iocb_flags(f); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); @@ -1184,7 +1184,15 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) int acc_mode = ACC_MODE(flags); BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS), - "struct open_flags doesn't yet handle flags > 32 bits"); + "VALID_OPEN_FLAGS must fit in 32 bits"); + /* The whole point: OPENAT2_REGULAR must be unrepresentable in int. */ + BUILD_BUG_ON_MSG(!upper_32_bits(OPENAT2_REGULAR), + "OPENAT2_REGULAR must live in the upper 32 bits of open_how::flags"); + /* Prevent a future bit collision between UAPI and internal carrier. */ + BUILD_BUG_ON_MSG(OPENAT2_REGULAR & VALID_OPEN_FLAGS, + "OPENAT2_REGULAR must not alias any open()/openat() flag"); + BUILD_BUG_ON_MSG(__O_REGULAR & VALID_OPENAT2_FLAGS, + "__O_REGULAR must not alias any user-visible flag"); /* * Strip flags that aren't relevant in determining struct open_flags. @@ -1196,7 +1204,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) * values before calling build_open_flags(), but openat2(2) checks all * of its arguments. */ - if (flags & ~VALID_OPEN_FLAGS) + if (flags & ~VALID_OPENAT2_FLAGS) return -EINVAL; if (how->resolve & ~VALID_RESOLVE_FLAGS) return -EINVAL; @@ -1236,6 +1244,14 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) if (!(acc_mode & MAY_WRITE)) return -EINVAL; } + /* + * Asking to open a directory and a regular file at the same time is + * contradictory. + */ + if ((flags & (O_DIRECTORY | OPENAT2_REGULAR)) == + (O_DIRECTORY | OPENAT2_REGULAR)) + return -EINVAL; + if (flags & O_PATH) { /* O_PATH only permits certain other flags to be set. */ if (flags & ~O_PATH_FLAGS) @@ -1252,6 +1268,19 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) if (flags & __O_SYNC) flags |= O_DSYNC; + /* + * Translate the upper-32-bit UAPI bit OPENAT2_REGULAR into the + * kernel-internal lower-32-bit __O_REGULAR carrier so the bit + * survives the assignment to op->open_flag (an int) below and the + * subsequent flow through f->f_flags (unsigned int) and the + * i_op->atomic_open() callback (unsigned). do_dentry_open() strips + * __O_REGULAR before the file becomes visible to userspace. + */ + if (flags & OPENAT2_REGULAR) { + flags &= ~OPENAT2_REGULAR; + flags |= __O_REGULAR; + } + op->open_flag = flags; /* O_TRUNC implies we need access checks for write permissions */ diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index e4295a5b55b3..88a4a1787ff0 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -241,6 +241,12 @@ static int __cifs_do_create(struct inode *dir, struct dentry *direntry, goto cifs_create_get_file_info; } + if ((oflags & __O_REGULAR) && !S_ISREG(newinode->i_mode)) { + CIFSSMBClose(xid, tcon, fid->netfid); + iput(newinode); + return -EFTYPE; + } + if (S_ISDIR(newinode->i_mode)) { CIFSSMBClose(xid, tcon, fid->netfid); iput(newinode); @@ -458,9 +464,15 @@ cifs_create_set_dentry: goto out_err; } - if (newinode && S_ISDIR(newinode->i_mode)) { - rc = -EISDIR; - goto out_err; + if (newinode) { + if ((oflags & __O_REGULAR) && !S_ISREG(newinode->i_mode)) { + rc = -EFTYPE; + goto out_err; + } + if (S_ISDIR(newinode->i_mode)) { + rc = -EISDIR; + goto out_err; + } } *inode = newinode; diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index c65c5c73d362..6ad6b9e7a226 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -4,6 +4,7 @@ #include #include +#include /* List of all valid flags for the open/openat flags argument: */ #define VALID_OPEN_FLAGS \ @@ -12,6 +13,23 @@ FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \ O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE | O_EMPTYPATH) +/* List of all valid flags for openat2(2)'s how->flags argument. */ +#define VALID_OPENAT2_FLAGS (VALID_OPEN_FLAGS | OPENAT2_REGULAR) + +/* + * Kernel-internal carrier for OPENAT2_REGULAR. The UAPI bit lives in the + * upper 32 bits of open_how::flags so open()/openat() cannot encode it. + * build_open_flags() translates it to this internal flag, which then + * propagates through op->open_flag and f->f_flags exactly like __FMODE_EXEC. + * do_dentry_open() strips it so userspace cannot observe it via + * fcntl(F_GETFL). + * + * Bit 30 is not claimed by any O_* flag on any architecture and stays clear + * of the sign bit of the int op->open_flag. fcntl_init() enforces that it + * never aliases an open-flag bit. + */ +#define __O_REGULAR (1 << 30) + /* List of all valid flags for the how->resolve argument: */ #define VALID_RESOLVE_FLAGS \ (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h index a5feb7604948..575c2c59d14a 100644 --- a/include/uapi/linux/openat2.h +++ b/include/uapi/linux/openat2.h @@ -22,6 +22,13 @@ struct open_how { __u64 resolve; }; +/* + * how->flags bits exclusive to openat2(2). These live in the upper 32 bits + * of @flags so that they cannot be expressed by open(2) / openat(2), whose + * @flags argument is a C int. + */ +#define OPENAT2_REGULAR ((__u64)1 << 32) /* Only open regular files. */ + /* how->resolve flags for openat2(2). */ #define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings (includes bind-mounts). */ -- cgit v1.3-14-g43fede From 0719e10d826aa0ba4840917d0261986eaead9a51 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 19 May 2026 12:44:32 +0100 Subject: io_uring/zcrx: notify user when out of buffers There are currently no easy ways for the user to know if zcrx is out of buffers and page pool fails to allocate. Add uapi for zcrx to communicate it back. It's implemented as a separate CQE, which for now is posted to the creator ctx. To use it, on registration the user space needs to pass an instance of struct zcrx_notification_desc, which tells the kernel the user_data for resulting CQEs and which event types are expected / allowed. When an allowed event happens, zcrx will post a CQE containing the specified user_data, and lower bits of cqe->res will be set to the event mask. Before the kernel could post another notification of the given type, the user needs to acknowledge that it processed the previous one by issuing IORING_REGISTER_ZCRX_CTRL with ZCRX_CTRL_ARM_NOTIFICATION. The only notification type the patch implements is ZCRX_NOTIF_NO_BUFFERS, but we'll need more of them in the future. Co-developed-by: Vishwanath Seshagiri Signed-off-by: Pavel Begunkov Signed-off-by: Vishwanath Seshagiri Link: https://patch.msgid.link/35cd307a03a43583838a2e151fc641c69abd786f.1779189667.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/zcrx.h | 24 ++++++++++- io_uring/io_uring.c | 2 +- io_uring/io_uring.h | 1 + io_uring/zcrx.c | 86 +++++++++++++++++++++++++++++++++++++- io_uring/zcrx.h | 7 +++- 5 files changed, 115 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/zcrx.h b/include/uapi/linux/io_uring/zcrx.h index 5ce02c7a6096..67185566ad3c 100644 --- a/include/uapi/linux/io_uring/zcrx.h +++ b/include/uapi/linux/io_uring/zcrx.h @@ -65,6 +65,20 @@ enum zcrx_features { * value in struct io_uring_zcrx_ifq_reg::rx_buf_len. */ ZCRX_FEATURE_RX_PAGE_SIZE = 1 << 0, + ZCRX_FEATURE_NOTIFICATION = 1 << 1, +}; + +enum zcrx_notification_type { + ZCRX_NOTIF_NO_BUFFERS, + + __ZCRX_NOTIF_TYPE_LAST, +}; + +struct zcrx_notification_desc { + __u64 user_data; + __u32 type_mask; + __u32 __resv1; + __u64 __resv2[10]; }; /* @@ -82,12 +96,14 @@ struct io_uring_zcrx_ifq_reg { struct io_uring_zcrx_offsets offsets; __u32 zcrx_id; __u32 rx_buf_len; - __u64 __resv[3]; + __u64 notif_desc; /* see struct zcrx_notification_desc */ + __u64 __resv[2]; }; enum zcrx_ctrl_op { ZCRX_CTRL_FLUSH_RQ, ZCRX_CTRL_EXPORT, + ZCRX_CTRL_ARM_NOTIFICATION, __ZCRX_CTRL_LAST, }; @@ -101,6 +117,11 @@ struct zcrx_ctrl_export { __u32 __resv1[11]; }; +struct zcrx_ctrl_arm_notif { + __u32 notif_type; + __u32 __resv[11]; +}; + struct zcrx_ctrl { __u32 zcrx_id; __u32 op; /* see enum zcrx_ctrl_op */ @@ -109,6 +130,7 @@ struct zcrx_ctrl { union { struct zcrx_ctrl_export zc_export; struct zcrx_ctrl_flush_rq zc_flush; + struct zcrx_ctrl_arm_notif zc_arm_notif; }; }; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index fb6ed52bae61..02c02e14f392 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -160,7 +160,7 @@ static void io_poison_cached_req(struct io_kiocb *req) req->apoll = IO_URING_PTR_POISON; } -static void io_poison_req(struct io_kiocb *req) +void io_poison_req(struct io_kiocb *req) { io_poison_cached_req(req); req->async_data = IO_URING_PTR_POISON; diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 1b657b714373..cb736b815422 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -213,6 +213,7 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx); void io_activate_pollwq(struct io_ring_ctx *ctx); void io_restriction_clone(struct io_restriction *dst, struct io_restriction *src); +void io_poison_req(struct io_kiocb *req); static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) { diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 1e194de7d6d2..2bca9a58dcf6 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -766,6 +766,8 @@ static int import_zcrx(struct io_ring_ctx *ctx, return -EINVAL; if (reg->if_rxq || reg->rq_entries || reg->area_ptr || reg->region_ptr) return -EINVAL; + if (reg->notif_desc) + return -EINVAL; if (reg->flags & ~ZCRX_REG_IMPORT) return -EINVAL; @@ -854,6 +856,7 @@ netdev_put_unlock: int io_register_zcrx(struct io_ring_ctx *ctx, struct io_uring_zcrx_ifq_reg __user *arg) { + struct zcrx_notification_desc notif; struct io_uring_zcrx_area_reg area; struct io_uring_zcrx_ifq_reg reg; struct io_uring_region_desc rd; @@ -897,10 +900,22 @@ int io_register_zcrx(struct io_ring_ctx *ctx, if (copy_from_user(&area, u64_to_user_ptr(reg.area_ptr), sizeof(area))) return -EFAULT; + memset(¬if, 0, sizeof(notif)); + if (reg.notif_desc && copy_from_user(¬if, u64_to_user_ptr(reg.notif_desc), + sizeof(notif))) + return -EFAULT; + if (notif.type_mask & ~ZCRX_NOTIF_TYPE_MASK) + return -EINVAL; + if (notif.__resv1 || !mem_is_zero(¬if.__resv2, sizeof(notif.__resv2))) + return -EINVAL; + ifq = io_zcrx_ifq_alloc(ctx); if (!ifq) return -ENOMEM; + ifq->notif_data = notif.user_data; + ifq->allowed_notif_mask = notif.type_mask; + if (ctx->user) { get_uid(ctx->user); ifq->user = ctx->user; @@ -952,7 +967,8 @@ int io_register_zcrx(struct io_ring_ctx *ctx, goto err; } - zcrx_set_ring_ctx(ifq, ctx); + if (notif.type_mask) + zcrx_set_ring_ctx(ifq, ctx); return 0; err: scoped_guard(mutex, &ctx->mmap_lock) @@ -1125,6 +1141,48 @@ static unsigned io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *if return allocated; } +static void zcrx_notif_tw(struct io_tw_req tw_req, io_tw_token_t tw) +{ + struct io_kiocb *req = tw_req.req; + struct io_ring_ctx *ctx = req->ctx; + + io_post_aux_cqe(ctx, req->cqe.user_data, req->cqe.res, 0); + percpu_ref_put(&ctx->refs); + io_poison_req(req); + kmem_cache_free(req_cachep, req); +} + +static void zcrx_send_notif(struct io_zcrx_ifq *ifq, unsigned type) +{ + gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN | __GFP_ZERO; + u32 type_mask = 1 << type; + struct io_kiocb *req; + + if (!(type_mask & ifq->allowed_notif_mask)) + return; + + guard(spinlock_bh)(&ifq->ctx_lock); + if (!ifq->master_ctx) + return; + if (type_mask & ifq->fired_notifs) + return; + + req = kmem_cache_alloc(req_cachep, gfp); + if (unlikely(!req)) + return; + + ifq->fired_notifs |= type_mask; + + req->opcode = IORING_OP_NOP; + req->cqe.user_data = ifq->notif_data; + req->cqe.res = type; + req->ctx = ifq->master_ctx; + percpu_ref_get(&req->ctx->refs); + req->tctx = NULL; + req->io_task_work.func = zcrx_notif_tw; + io_req_task_work_add(req); +} + static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp) { struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp); @@ -1141,8 +1199,10 @@ static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp) goto out_return; allocated = io_zcrx_refill_slow(pp, ifq, netmems, to_alloc); - if (!allocated) + if (!allocated) { + zcrx_send_notif(ifq, ZCRX_NOTIF_NO_BUFFERS); return 0; + } out_return: zcrx_sync_for_device(pp, ifq, netmems, allocated); allocated--; @@ -1291,12 +1351,32 @@ static int zcrx_flush_rq(struct io_ring_ctx *ctx, struct io_zcrx_ifq *zcrx, return 0; } +static int zcrx_arm_notif(struct io_ring_ctx *ctx, struct io_zcrx_ifq *zcrx, + struct zcrx_ctrl *ctrl) +{ + const struct zcrx_ctrl_arm_notif *an = &ctrl->zc_arm_notif; + unsigned type_mask; + + if (an->notif_type >= __ZCRX_NOTIF_TYPE_LAST) + return -EINVAL; + if (!mem_is_zero(&an->__resv, sizeof(an->__resv))) + return -EINVAL; + + guard(spinlock_bh)(&zcrx->ctx_lock); + type_mask = 1U << an->notif_type; + if (type_mask & ~zcrx->fired_notifs) + return -EINVAL; + zcrx->fired_notifs &= ~type_mask; + return 0; +} + int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { struct zcrx_ctrl ctrl; struct io_zcrx_ifq *zcrx; BUILD_BUG_ON(sizeof(ctrl.zc_export) != sizeof(ctrl.zc_flush)); + BUILD_BUG_ON(sizeof(ctrl.zc_export) != sizeof(ctrl.zc_arm_notif)); if (nr_args) return -EINVAL; @@ -1314,6 +1394,8 @@ int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) return zcrx_flush_rq(ctx, zcrx, &ctrl); case ZCRX_CTRL_EXPORT: return zcrx_export(ctx, zcrx, &ctrl, arg); + case ZCRX_CTRL_ARM_NOTIFICATION: + return zcrx_arm_notif(ctx, zcrx, &ctrl); } return -EOPNOTSUPP; diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index 76389a5dd50f..e8b7717d6adf 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -9,7 +9,9 @@ #include #define ZCRX_SUPPORTED_REG_FLAGS (ZCRX_REG_IMPORT | ZCRX_REG_NODEV) -#define ZCRX_FEATURES (ZCRX_FEATURE_RX_PAGE_SIZE) +#define ZCRX_FEATURES (ZCRX_FEATURE_RX_PAGE_SIZE |\ + ZCRX_FEATURE_NOTIFICATION) +#define ZCRX_NOTIF_TYPE_MASK (1U << ZCRX_NOTIF_NO_BUFFERS) struct io_zcrx_mem { unsigned long size; @@ -75,6 +77,9 @@ struct io_zcrx_ifq { spinlock_t ctx_lock; struct io_ring_ctx *master_ctx; + u32 allowed_notif_mask; + u32 fired_notifs; + u64 notif_data; }; #if defined(CONFIG_IO_URING_ZCRX) -- cgit v1.3-14-g43fede From 255180f7034f48aa5b0c8df70228307394bddbb9 Mon Sep 17 00:00:00 2001 From: Clément Léger Date: Tue, 19 May 2026 12:44:33 +0100 Subject: io_uring/zcrx: notify user on frag copy fallback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a ZCRX_NOTIF_COPY notification type to signal userspace when a received fragment could not be delivered using zero-copy and was instead copied into a buffer. Signed-off-by: Clément Léger Signed-off-by: Pavel Begunkov Link: https://patch.msgid.link/3d54bcd8bf10b3a1e88beb0cd39c40c3937bea4f.1779189667.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/zcrx.h | 1 + io_uring/zcrx.c | 7 ++++++- io_uring/zcrx.h | 2 +- 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/zcrx.h b/include/uapi/linux/io_uring/zcrx.h index 67185566ad3c..3f7b72b09878 100644 --- a/include/uapi/linux/io_uring/zcrx.h +++ b/include/uapi/linux/io_uring/zcrx.h @@ -70,6 +70,7 @@ enum zcrx_features { enum zcrx_notification_type { ZCRX_NOTIF_NO_BUFFERS, + ZCRX_NOTIF_COPY, __ZCRX_NOTIF_TYPE_LAST, }; diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 2bca9a58dcf6..404f9e7574a2 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -1532,8 +1532,13 @@ static int io_zcrx_copy_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq, const skb_frag_t *frag, int off, int len) { struct page *page = skb_frag_page(frag); + int ret; + + ret = io_zcrx_copy_chunk(req, ifq, page, off + skb_frag_off(frag), len); + if (ret > 0) + zcrx_send_notif(ifq, ZCRX_NOTIF_COPY); - return io_zcrx_copy_chunk(req, ifq, page, off + skb_frag_off(frag), len); + return ret; } static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq, diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index e8b7717d6adf..54d91b580eaf 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -11,7 +11,7 @@ #define ZCRX_SUPPORTED_REG_FLAGS (ZCRX_REG_IMPORT | ZCRX_REG_NODEV) #define ZCRX_FEATURES (ZCRX_FEATURE_RX_PAGE_SIZE |\ ZCRX_FEATURE_NOTIFICATION) -#define ZCRX_NOTIF_TYPE_MASK (1U << ZCRX_NOTIF_NO_BUFFERS) +#define ZCRX_NOTIF_TYPE_MASK ((1U << ZCRX_NOTIF_NO_BUFFERS) | (1U << ZCRX_NOTIF_COPY)) struct io_zcrx_mem { unsigned long size; -- cgit v1.3-14-g43fede From 6935f631465f5f60205978a59228a26db4723d51 Mon Sep 17 00:00:00 2001 From: Clément Léger Date: Tue, 19 May 2026 12:44:34 +0100 Subject: io_uring/zcrx: add shared-memory notification statistics MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for an optional stats struct embedded in the refill queue region, allowing userspace to monitor copy-fallback in real-time. Userspace queries the stats struct size and alignment via IO_URING_QUERY_ZCRX_NOTIF (notif_stats_size / notif_stats_alignment), then provides a stats_offset in zcrx_notification_desc pointing to a location within the refill queue region. The kernel updates the stats counters in-place on every copy-fallback event. Signed-off-by: Clément Léger [pavel: rename io_uring_zcrx_notif_stats] Signed-off-by: Pavel Begunkov Link: https://patch.msgid.link/f6af5a21015efea4b733b9d77aba22c637788fe4.1779189667.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/query.h | 12 +++++++++ include/uapi/linux/io_uring/zcrx.h | 15 +++++++++-- io_uring/query.c | 16 +++++++++++ io_uring/zcrx.c | 54 +++++++++++++++++++++++++++++++++++-- io_uring/zcrx.h | 1 + 5 files changed, 94 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index 95500759cc13..1a68eca7c6b4 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -23,6 +23,7 @@ enum { IO_URING_QUERY_OPCODES = 0, IO_URING_QUERY_ZCRX = 1, IO_URING_QUERY_SCQ = 2, + IO_URING_QUERY_ZCRX_NOTIF = 3, __IO_URING_QUERY_MAX, }; @@ -62,6 +63,17 @@ struct io_uring_query_zcrx { __u64 __resv2; }; +struct io_uring_query_zcrx_notif { + /* Bitmask of supported ZCRX_NOTIF_* flags */ + __u32 notif_flags; + /* Size of io_uring_zcrx_notif_stats */ + __u32 notif_stats_size; + /* Required alignment for the stats struct within the region (ie stats_offset) */ + __u32 notif_stats_off_alignment; + __u32 __resv1; + __u64 __resv2[4]; +}; + struct io_uring_query_scq { /* The SQ/CQ rings header size */ __u64 hdr_size; diff --git a/include/uapi/linux/io_uring/zcrx.h b/include/uapi/linux/io_uring/zcrx.h index 3f7b72b09878..15c05c45ce36 100644 --- a/include/uapi/linux/io_uring/zcrx.h +++ b/include/uapi/linux/io_uring/zcrx.h @@ -75,11 +75,22 @@ enum zcrx_notification_type { __ZCRX_NOTIF_TYPE_LAST, }; +enum zcrx_notification_desc_flags { + /* If set, stats_offset holds a valid offset to a notif_stats struct */ + ZCRX_NOTIF_DESC_FLAG_STATS = 1 << 0, +}; + +struct zcrx_notif_stats { + __u64 copy_count; /* cumulative copy-fallback CQEs */ + __u64 copy_bytes; /* cumulative bytes copied */ +}; + struct zcrx_notification_desc { __u64 user_data; __u32 type_mask; - __u32 __resv1; - __u64 __resv2[10]; + __u32 flags; /* see enum zcrx_notification_desc_flags */ + __u64 stats_offset; /* offset from the beginning of refill ring region for stats */ + __u64 __resv2[9]; }; /* diff --git a/io_uring/query.c b/io_uring/query.c index c1704d088374..d529d94aa8f4 100644 --- a/io_uring/query.c +++ b/io_uring/query.c @@ -9,6 +9,7 @@ union io_query_data { struct io_uring_query_opcode opcodes; struct io_uring_query_zcrx zcrx; + struct io_uring_query_zcrx_notif zcrx_notif; struct io_uring_query_scq scq; }; @@ -44,6 +45,18 @@ static ssize_t io_query_zcrx(union io_query_data *data) return sizeof(*e); } +static ssize_t io_query_zcrx_notif(union io_query_data *data) +{ + struct io_uring_query_zcrx_notif *e = &data->zcrx_notif; + + e->notif_flags = ZCRX_NOTIF_TYPE_MASK; + e->notif_stats_size = sizeof(struct zcrx_notif_stats); + e->notif_stats_off_alignment = __alignof__(struct zcrx_notif_stats); + e->__resv1 = 0; + memset(&e->__resv2, 0, sizeof(e->__resv2)); + return sizeof(*e); +} + static ssize_t io_query_scq(union io_query_data *data) { struct io_uring_query_scq *e = &data->scq; @@ -83,6 +96,9 @@ static int io_handle_query_entry(union io_query_data *data, void __user *uhdr, case IO_URING_QUERY_ZCRX: ret = io_query_zcrx(data); break; + case IO_URING_QUERY_ZCRX_NOTIF: + ret = io_query_zcrx_notif(data); + break; case IO_URING_QUERY_SCQ: ret = io_query_scq(data); break; diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 404f9e7574a2..6bd71435e475 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -415,6 +415,7 @@ static void io_free_rbuf_ring(struct io_zcrx_ifq *ifq) io_free_region(ifq->user, &ifq->rq_region); ifq->rq.ring = IO_URING_PTR_POISON; ifq->rq.rqes = IO_URING_PTR_POISON; + ifq->notif_stats = IO_URING_PTR_POISON; } static void io_zcrx_free_area(struct io_zcrx_ifq *ifq, @@ -853,6 +854,33 @@ netdev_put_unlock: return ret; } +static int zcrx_validate_notif_stats(struct io_zcrx_ifq *ifq, + const struct io_uring_zcrx_ifq_reg *reg, + const struct zcrx_notification_desc *notif) +{ + size_t stats_off = notif->stats_offset; + size_t used, end; + + used = reg->offsets.rqes + + sizeof(struct io_uring_zcrx_rqe) * reg->rq_entries; + + if (!IS_ALIGNED(stats_off, __alignof__(struct zcrx_notif_stats))) + return -EINVAL; + if (stats_off < used) + return -ERANGE; + if (check_add_overflow(stats_off, + sizeof(struct zcrx_notif_stats), + &end)) + return -ERANGE; + if (end > io_region_size(&ifq->rq_region)) + return -ERANGE; + + ifq->notif_stats = io_region_get_ptr(&ifq->rq_region) + stats_off; + memset(ifq->notif_stats, 0, sizeof(*ifq->notif_stats)); + + return 0; +} + int io_register_zcrx(struct io_ring_ctx *ctx, struct io_uring_zcrx_ifq_reg __user *arg) { @@ -906,7 +934,13 @@ int io_register_zcrx(struct io_ring_ctx *ctx, return -EFAULT; if (notif.type_mask & ~ZCRX_NOTIF_TYPE_MASK) return -EINVAL; - if (notif.__resv1 || !mem_is_zero(¬if.__resv2, sizeof(notif.__resv2))) + if (notif.flags & ~ZCRX_NOTIF_DESC_FLAG_STATS) + return -EINVAL; + if (!(notif.flags & ZCRX_NOTIF_DESC_FLAG_STATS)) { + if (notif.stats_offset) + return -EINVAL; + } + if (!mem_is_zero(¬if.__resv2, sizeof(notif.__resv2))) return -EINVAL; ifq = io_zcrx_ifq_alloc(ctx); @@ -937,6 +971,12 @@ int io_register_zcrx(struct io_ring_ctx *ctx, if (ret) goto err; + if (notif.flags & ZCRX_NOTIF_DESC_FLAG_STATS) { + ret = zcrx_validate_notif_stats(ifq, ®, ¬if); + if (ret) + goto err; + } + ifq->kern_readable = !(area.flags & IORING_ZCRX_AREA_DMABUF); if (!(reg.flags & ZCRX_REG_NODEV)) { @@ -1152,6 +1192,11 @@ static void zcrx_notif_tw(struct io_tw_req tw_req, io_tw_token_t tw) kmem_cache_free(req_cachep, req); } +static void zcrx_stat_add(__u64 *p, s64 v) +{ + WRITE_ONCE(*p, READ_ONCE(*p) + v); +} + static void zcrx_send_notif(struct io_zcrx_ifq *ifq, unsigned type) { gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN | __GFP_ZERO; @@ -1535,8 +1580,13 @@ static int io_zcrx_copy_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq, int ret; ret = io_zcrx_copy_chunk(req, ifq, page, off + skb_frag_off(frag), len); - if (ret > 0) + if (ret > 0) { + if (ifq->notif_stats) { + zcrx_stat_add(&ifq->notif_stats->copy_count, 1); + zcrx_stat_add(&ifq->notif_stats->copy_bytes, ret); + } zcrx_send_notif(ifq, ZCRX_NOTIF_COPY); + } return ret; } diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index 54d91b580eaf..fa00900e479e 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -80,6 +80,7 @@ struct io_zcrx_ifq { u32 allowed_notif_mask; u32 fired_notifs; u64 notif_data; + struct zcrx_notif_stats *notif_stats; }; #if defined(CONFIG_IO_URING_ZCRX) -- cgit v1.3-14-g43fede From 0b13c6a618d09b20dbb1a33bc354764cbac6f2bd Mon Sep 17 00:00:00 2001 From: Tim Bird Date: Fri, 22 May 2026 16:55:08 -0600 Subject: llc: Add SPDX id lines to some llc source files Most of the lls source files are missing SPDX-License-Identifier lines. Add appropriate IDs to these files, and remove other license info from the header. In once case, leave the existing id line and just remove the license reference text. Signed-off-by: Tim Bird Link: https://patch.msgid.link/20260522225508.24006-1-tim.bird@sony.com Signed-off-by: Jakub Kicinski --- include/linux/llc.h | 8 +------- include/net/llc.h | 8 +------- include/uapi/linux/llc.h | 7 ------- net/llc/Makefile | 8 +------- net/llc/af_llc.c | 8 +------- net/llc/llc_c_ac.c | 8 +------- net/llc/llc_c_ev.c | 8 +------- net/llc/llc_c_st.c | 8 +------- net/llc/llc_conn.c | 8 +------- net/llc/llc_core.c | 8 +------- net/llc/llc_if.c | 8 +------- net/llc/llc_input.c | 8 +------- net/llc/llc_pdu.c | 8 +------- net/llc/llc_proc.c | 8 +------- net/llc/llc_s_ac.c | 8 +------- net/llc/llc_s_ev.c | 8 +------- net/llc/llc_s_st.c | 8 +------- net/llc/llc_sap.c | 8 +------- net/llc/llc_station.c | 8 +------- 19 files changed, 18 insertions(+), 133 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/llc.h b/include/linux/llc.h index b965314d017f..944e9e213112 100644 --- a/include/linux/llc.h +++ b/include/linux/llc.h @@ -1,14 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * IEEE 802.2 User Interface SAPs for Linux, data structures and indicators. * * Copyright (c) 2001 by Jay Schulist - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #ifndef __LINUX_LLC_H #define __LINUX_LLC_H diff --git a/include/net/llc.h b/include/net/llc.h index e250dca03963..029ba8a22319 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_H #define LLC_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include diff --git a/include/uapi/linux/llc.h b/include/uapi/linux/llc.h index cf8806b14d5f..2ffd81f9cc01 100644 --- a/include/uapi/linux/llc.h +++ b/include/uapi/linux/llc.h @@ -3,13 +3,6 @@ * IEEE 802.2 User Interface SAPs for Linux, data structures and indicators. * * Copyright (c) 2001 by Jay Schulist - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #ifndef _UAPI__LINUX_LLC_H #define _UAPI__LINUX_LLC_H diff --git a/net/llc/Makefile b/net/llc/Makefile index 5e0ef436daae..46b1cd905ffd 100644 --- a/net/llc/Makefile +++ b/net/llc/Makefile @@ -1,15 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 ########################################################################### # Makefile for the Linux 802.2 LLC (fully-functional) layer. # # Copyright (c) 1997 by Procom Technology,Inc. # 2001-2003 by Arnaldo Carvalho de Melo -# -# This program can be redistributed or modified under the terms of the -# GNU General Public License as published by the Free Software Foundation. -# This program is distributed without any warranty or implied warranty -# of merchantability or fitness for a particular purpose. -# -# See the GNU General Public License for more details. ########################################################################### obj-$(CONFIG_LLC) += llc.o diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 35278c519a30..8ed1be1ecccc 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * af_llc.c - LLC User Interface SAPs * Description: @@ -12,13 +13,6 @@ * * Copyright (c) 2001 by Jay Schulist * 2002-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index ab86c720b3ec..724ecd741d4c 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_c_ac.c - actions performed during connection state transition. * @@ -9,13 +10,6 @@ * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include diff --git a/net/llc/llc_c_ev.c b/net/llc/llc_c_ev.c index d6627a80cb45..beb2836c7db0 100644 --- a/net/llc/llc_c_ev.c +++ b/net/llc/llc_c_ev.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_c_ev.c - Connection component state transition event qualifiers * @@ -25,13 +26,6 @@ * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include diff --git a/net/llc/llc_c_st.c b/net/llc/llc_c_st.c index 1c267db304df..5fbd8d19c6c4 100644 --- a/net/llc/llc_c_st.c +++ b/net/llc/llc_c_st.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_c_st.c - This module contains state transition of connection component. * @@ -6,13 +7,6 @@ * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 5c0ac243b248..e8f427375c68 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_conn.c - Driver routines for connection component. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index d73f5414d8ce..5b0f1986bddc 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_core.c - Minimum needed routines for sap handling and module init/exit * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index 58a5f419adc6..1514362e613d 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_if.c - Defines LLC interface to upper layer * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index 61b0159b2fbe..8eb3d73c39d1 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_input.c - Minimal input path for LLC * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include diff --git a/net/llc/llc_pdu.c b/net/llc/llc_pdu.c index 63749dde542f..c1938fa24a3f 100644 --- a/net/llc/llc_pdu.c +++ b/net/llc/llc_pdu.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_pdu.c - access to PDU internals * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index aa81c67b24a1..4804a08c2490 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * proc_llc.c - proc interface for LLC * * Copyright (c) 2001 by Jay Schulist * 2002-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index 7a0cae9a8111..98deee560373 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_s_ac.c - actions performed during sap state transition. * @@ -9,13 +10,6 @@ * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include diff --git a/net/llc/llc_s_ev.c b/net/llc/llc_s_ev.c index a74d2a1d6581..cfbecba589e7 100644 --- a/net/llc/llc_s_ev.c +++ b/net/llc/llc_s_ev.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_s_ev.c - Defines SAP component events * @@ -6,13 +7,6 @@ * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include diff --git a/net/llc/llc_s_st.c b/net/llc/llc_s_st.c index acccc827c562..e14d4f520327 100644 --- a/net/llc/llc_s_st.c +++ b/net/llc/llc_s_st.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_s_st.c - Defines SAP component state machine transitions. * @@ -6,13 +7,6 @@ * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 6cd03c2ae7d5..1bd446a21092 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_sap.c - driver routines for SAP component. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index f50654292510..77fd0ac75263 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * llc_station.c - station component of LLC * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include #include -- cgit v1.3-14-g43fede From 91561e1dc94b8a33857370ef3c5b5523c4461d5b Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Thu, 21 May 2026 13:34:20 -0700 Subject: PCI: Add pci_ats_required() for CXL.cache capable devices Controlled by IOMMU drivers, ATS can be enabled "on demand", when a given PASID on a device is attached to an I/O page table. This is working, even when a device has no translation on its RID (i.e., RID is IOMMU bypassed). However, certain PCIe devices require non-PASID ATS on their RID even when the RID is IOMMU bypassed. Call this "ATS always on" in IOMMU term. For example, CXL spec r4.0 notes in sec 3.2.5.13 Memory Type on CXL.cache: "To source requests on CXL.cache, devices need to get the Host Physical Address (HPA) from the Host by means of an ATS request on CXL.io." In other words, the CXL.cache capability requires ATS; otherwise, it can't access host physical memory. Introduce a new pci_ats_required() helper for the IOMMU driver to scan a PCI device and shift ATS policies between "on demand" and "always on". Add the support for CXL.cache devices first. Pre-CXL devices will be added in quirks.c file. Note that pci_ats_required() validates against pci_ats_supported(), so we ensure that untrusted devices (e.g. external ports) will not be always on. This maintains the existing ATS security policy regarding potential side- channel attacks via ATS. Cc: linux-cxl@vger.kernel.org Suggested-by: Vikram Sethi Suggested-by: Jason Gunthorpe Reviewed-by: Jonathan Cameron Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Tested-by: Nirmoy Das Acked-by: Nirmoy Das Reviewed-by: Dave Jiang Acked-by: Bjorn Helgaas Signed-off-by: Nicolin Chen Reviewed-by: Yi Liu Signed-off-by: Joerg Roedel --- drivers/pci/ats.c | 46 +++++++++++++++++++++++++++++++++++++++++++ include/linux/pci-ats.h | 3 +++ include/uapi/linux/pci_regs.h | 1 + 3 files changed, 50 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index ec6c8dbdc5e9..84cd06d74fc9 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -205,6 +205,52 @@ int pci_ats_page_aligned(struct pci_dev *pdev) return 0; } +/* + * CXL r4.0, sec 3.2.5.13 Memory Type on CXL.cache notes: to source requests on + * CXL.cache, devices need to get the Host Physical Address (HPA) from the Host + * by means of an ATS request on CXL.io. + * + * In other words, CXL.cache devices cannot access host physical memory without + * ATS. + * + * Check Cache_Capable instead of Cache_Enable because CXL.cache may be enabled + * after the caller uses this to make its ATS decision. + */ +static bool pci_cxl_ats_required(struct pci_dev *pdev) +{ + int offset; + u16 cap; + + offset = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL, + PCI_DVSEC_CXL_DEVICE); + if (!offset) + return false; + + if (pci_read_config_word(pdev, offset + PCI_DVSEC_CXL_CAP, &cap)) + return false; + + return cap & PCI_DVSEC_CXL_CACHE_CAPABLE; +} + +/** + * pci_ats_required - Whether the PCI device requires ATS + * @pdev: the PCI device + * + * Returns true, if the PCI device requires ATS for basic functional operation. + */ +bool pci_ats_required(struct pci_dev *pdev) +{ + if (!pci_ats_supported(pdev)) + return false; + + /* A VF inherits its PF's requirement for ATS function */ + if (pdev->is_virtfn) + pdev = pci_physfn(pdev); + + return pci_cxl_ats_required(pdev); +} +EXPORT_SYMBOL_GPL(pci_ats_required); + #ifdef CONFIG_PCI_PRI void pci_pri_init(struct pci_dev *pdev) { diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 75c6c86cf09d..f3723b686129 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -12,6 +12,7 @@ int pci_prepare_ats(struct pci_dev *dev, int ps); void pci_disable_ats(struct pci_dev *dev); int pci_ats_queue_depth(struct pci_dev *dev); int pci_ats_page_aligned(struct pci_dev *dev); +bool pci_ats_required(struct pci_dev *dev); #else /* CONFIG_PCI_ATS */ static inline bool pci_ats_supported(struct pci_dev *d) { return false; } @@ -24,6 +25,8 @@ static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } static inline int pci_ats_page_aligned(struct pci_dev *dev) { return 0; } +static inline bool pci_ats_required(struct pci_dev *dev) +{ return false; } #endif /* CONFIG_PCI_ATS */ #ifdef CONFIG_PCI_PRI diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 14f634ab9350..6ac45be1008b 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1349,6 +1349,7 @@ /* CXL r4.0, 8.1.3: PCIe DVSEC for CXL Device */ #define PCI_DVSEC_CXL_DEVICE 0 #define PCI_DVSEC_CXL_CAP 0xA +#define PCI_DVSEC_CXL_CACHE_CAPABLE _BITUL(0) #define PCI_DVSEC_CXL_MEM_CAPABLE _BITUL(2) #define PCI_DVSEC_CXL_HDM_COUNT __GENMASK(5, 4) #define PCI_DVSEC_CXL_CTRL 0xC -- cgit v1.3-14-g43fede From 622775dbc56a6349fc98b368041e3224bfeeb9de Mon Sep 17 00:00:00 2001 From: Liviu Stan Date: Mon, 25 May 2026 19:39:34 +0300 Subject: iio: core: Add IIO_COVERAGE channel type Add a new channel type for sensors that report fractional coverage as a percentage. The sysfs attribute is in_coverageY_raw; after applying in_coverageY_scale the value is in percent. The first user is the ADT7604 leak detector, where the value represents the portion of the sensing element that is wetted. Signed-off-by: Liviu Stan Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 17 +++++++++++++++++ drivers/iio/industrialio-core.c | 1 + include/uapi/linux/iio/types.h | 1 + tools/iio/iio_event_monitor.c | 2 ++ 4 files changed, 21 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 925a33fd309a..d8d6d85235b0 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1980,6 +1980,23 @@ Description: Raw (unscaled no offset etc.) resistance reading. Units after application of scale and offset are ohms. +What: /sys/bus/iio/devices/iio:deviceX/in_coverageY_raw +KernelVersion: 7.2 +Contact: linux-iio@vger.kernel.org +Description: + Raw (unscaled no offset etc.) coverage reading. Used for sensors + that report fractional coverage as a percentage, such as leak + detectors where the value represents what portion of the sensing + element is wetted. Units after application of scale and offset are + percent. + +What: /sys/bus/iio/devices/iio:deviceX/in_coverageY_scale +KernelVersion: 7.2 +Contact: linux-iio@vger.kernel.org +Description: + Scale to be applied to in_coverageY_raw to obtain coverage + in percent. + What: /sys/bus/iio/devices/iio:deviceX/heater_enable KernelVersion: 4.1.0 Contact: linux-iio@vger.kernel.org diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index bd6f4f9f4533..ffe0dc49c4b9 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -98,6 +98,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_CHROMATICITY] = "chromaticity", [IIO_ATTENTION] = "attention", [IIO_ALTCURRENT] = "altcurrent", + [IIO_COVERAGE] = "coverage", }; static const char * const iio_modifier_names[] = { diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index d7c2bb223651..c9295c707041 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -53,6 +53,7 @@ enum iio_chan_type { IIO_CHROMATICITY, IIO_ATTENTION, IIO_ALTCURRENT, + IIO_COVERAGE, }; enum iio_modifier { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index df6c43d7738d..bc3ef4c77c2b 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -65,6 +65,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_CHROMATICITY] = "chromaticity", [IIO_ATTENTION] = "attention", [IIO_ALTCURRENT] = "altcurrent", + [IIO_COVERAGE] = "coverage", }; static const char * const iio_ev_type_text[] = { @@ -194,6 +195,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_CHROMATICITY: case IIO_ATTENTION: case IIO_ALTCURRENT: + case IIO_COVERAGE: break; default: return false; -- cgit v1.3-14-g43fede From 4c08a9f38c50c0df7091b5567be7a3bbac92de0b Mon Sep 17 00:00:00 2001 From: Luca Boccassi Date: Wed, 29 Apr 2026 22:21:16 +0100 Subject: liveupdate: add LIVEUPDATE_SESSION_GET_NAME ioctl Userspace when requesting a session via the ioctl specifies a name and gets a FD, but then there is no ioctl to go back the other way and get the name given a LUO session FD. This is problematic especially when there is a userspace orchestrator that wants to check what FDs it is handling for clients without having to do manual string scraping of procfs, or without procfs at all. Add a ioctl to simply get the name from an FD. Signed-off-by: Luca Boccassi Reviewed-by: Pasha Tatashin Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20260429212221.814107-4-luca.boccassi@gmail.com Signed-off-by: Pasha Tatashin Signed-off-by: Mike Rapoport (Microsoft) --- include/uapi/linux/liveupdate.h | 21 +++++++++++++++++++++ kernel/liveupdate/luo_session.c | 16 ++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/liveupdate.h b/include/uapi/linux/liveupdate.h index 30bc66ee9436..3a9ff53b02e0 100644 --- a/include/uapi/linux/liveupdate.h +++ b/include/uapi/linux/liveupdate.h @@ -59,6 +59,7 @@ enum { LIVEUPDATE_CMD_SESSION_PRESERVE_FD = LIVEUPDATE_CMD_SESSION_BASE, LIVEUPDATE_CMD_SESSION_RETRIEVE_FD = 0x41, LIVEUPDATE_CMD_SESSION_FINISH = 0x42, + LIVEUPDATE_CMD_SESSION_GET_NAME = 0x43, }; /** @@ -213,4 +214,24 @@ struct liveupdate_session_finish { #define LIVEUPDATE_SESSION_FINISH \ _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_SESSION_FINISH) +/** + * struct liveupdate_session_get_name - ioctl(LIVEUPDATE_SESSION_GET_NAME) + * @size: Input; sizeof(struct liveupdate_session_get_name) + * @reserved: Input; Must be zero. Reserved for future use. + * @name: Output; A null-terminated string with the full session name. + * + * Retrieves the full name of the session associated with this file descriptor. + * This is useful because the kernel may truncate the name shown in /proc. + * + * Return: 0 on success, negative error code on failure. + */ +struct liveupdate_session_get_name { + __u32 size; + __u32 reserved; + __u8 name[LIVEUPDATE_SESSION_NAME_LENGTH]; +}; + +#define LIVEUPDATE_SESSION_GET_NAME \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_SESSION_GET_NAME) + #endif /* _UAPI_LIVEUPDATE_H */ diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c index ec7aebc15a80..e7f27815c051 100644 --- a/kernel/liveupdate/luo_session.c +++ b/kernel/liveupdate/luo_session.c @@ -289,10 +289,24 @@ static int luo_session_finish(struct luo_session *session, return luo_ucmd_respond(ucmd, sizeof(*argp)); } +static int luo_session_get_name(struct luo_session *session, + struct luo_ucmd *ucmd) +{ + struct liveupdate_session_get_name *argp = ucmd->cmd; + + if (argp->reserved != 0) + return -EINVAL; + + strscpy((char *)argp->name, session->name, sizeof(argp->name)); + + return luo_ucmd_respond(ucmd, sizeof(*argp)); +} + union ucmd_buffer { struct liveupdate_session_finish finish; struct liveupdate_session_preserve_fd preserve; struct liveupdate_session_retrieve_fd retrieve; + struct liveupdate_session_get_name get_name; }; struct luo_ioctl_op { @@ -319,6 +333,8 @@ static const struct luo_ioctl_op luo_session_ioctl_ops[] = { struct liveupdate_session_preserve_fd, token), IOCTL_OP(LIVEUPDATE_SESSION_RETRIEVE_FD, luo_session_retrieve_fd, struct liveupdate_session_retrieve_fd, token), + IOCTL_OP(LIVEUPDATE_SESSION_GET_NAME, luo_session_get_name, + struct liveupdate_session_get_name, name), }; static long luo_session_ioctl(struct file *filep, unsigned int cmd, -- cgit v1.3-14-g43fede From af81cb247ca94e4bcfea31ea862cf3aaf955a503 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 25 Mar 2026 10:40:28 -0400 Subject: sunrpc: add a generic netlink family for cache upcalls The auth.unix.ip and auth.unix.gid caches live in the sunrpc module, so they cannot use the nfsd generic netlink family. Create a new "sunrpc" generic netlink family with its own "exportd" multicast group to support cache upcall notifications for sunrpc-resident caches. Define a YAML spec (sunrpc_cache.yaml) with a cache-type enum (ip_map, unix_gid), a cache-notify multicast event, and the corresponding uapi header. Implement sunrpc_cache_notify() in cache.c, which checks for listeners on the exportd multicast group, builds and sends a SUNRPC_CMD_CACHE_NOTIFY message with the cache-type attribute. Register/unregister the sunrpc_nl_family in init_sunrpc() and cleanup_sunrpc(). Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/sunrpc_cache.yaml | 40 ++++++++++++++++++++++++ include/linux/sunrpc/cache.h | 2 ++ include/uapi/linux/sunrpc_netlink.h | 35 +++++++++++++++++++++ net/sunrpc/Makefile | 2 +- net/sunrpc/cache.c | 44 +++++++++++++++++++++++++++ net/sunrpc/netlink.c | 34 +++++++++++++++++++++ net/sunrpc/netlink.h | 22 ++++++++++++++ net/sunrpc/sunrpc_syms.c | 10 ++++++ 8 files changed, 188 insertions(+), 1 deletion(-) create mode 100644 Documentation/netlink/specs/sunrpc_cache.yaml create mode 100644 include/uapi/linux/sunrpc_netlink.h create mode 100644 net/sunrpc/netlink.c create mode 100644 net/sunrpc/netlink.h (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/sunrpc_cache.yaml b/Documentation/netlink/specs/sunrpc_cache.yaml new file mode 100644 index 000000000000..f4aa699598bc --- /dev/null +++ b/Documentation/netlink/specs/sunrpc_cache.yaml @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +--- +name: sunrpc +protocol: genetlink +uapi-header: linux/sunrpc_netlink.h + +doc: SUNRPC cache upcall support over generic netlink. + +definitions: + - + type: flags + name: cache-type + entries: [ip_map, unix_gid] + +attribute-sets: + - + name: cache-notify + attributes: + - + name: cache-type + type: u32 + enum: cache-type + +operations: + list: + - + name: cache-notify + doc: Notification that there are cache requests that need servicing + attribute-set: cache-notify + mcgrp: exportd + event: + attributes: + - cache-type + +mcast-groups: + list: + - + name: none + - + name: exportd diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index f88dc6bb17c7..2735c332ddb7 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -256,6 +256,8 @@ int sunrpc_cache_requests_snapshot(struct cache_detail *cd, struct cache_head **items, u64 *seqnos, int max, u64 min_seqno); +int sunrpc_cache_notify(struct cache_detail *cd, struct cache_head *h, + u32 cache_type); /* Must store cache_detail in seq_file->private if using next three functions */ extern void *cache_seq_start_rcu(struct seq_file *file, loff_t *pos); diff --git a/include/uapi/linux/sunrpc_netlink.h b/include/uapi/linux/sunrpc_netlink.h new file mode 100644 index 000000000000..6135d9b3eef1 --- /dev/null +++ b/include/uapi/linux/sunrpc_netlink.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/sunrpc_cache.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _UAPI_LINUX_SUNRPC_NETLINK_H +#define _UAPI_LINUX_SUNRPC_NETLINK_H + +#define SUNRPC_FAMILY_NAME "sunrpc" +#define SUNRPC_FAMILY_VERSION 1 + +enum sunrpc_cache_type { + SUNRPC_CACHE_TYPE_IP_MAP = 1, + SUNRPC_CACHE_TYPE_UNIX_GID = 2, +}; + +enum { + SUNRPC_A_CACHE_NOTIFY_CACHE_TYPE = 1, + + __SUNRPC_A_CACHE_NOTIFY_MAX, + SUNRPC_A_CACHE_NOTIFY_MAX = (__SUNRPC_A_CACHE_NOTIFY_MAX - 1) +}; + +enum { + SUNRPC_CMD_CACHE_NOTIFY = 1, + + __SUNRPC_CMD_MAX, + SUNRPC_CMD_MAX = (__SUNRPC_CMD_MAX - 1) +}; + +#define SUNRPC_MCGRP_NONE "none" +#define SUNRPC_MCGRP_EXPORTD "exportd" + +#endif /* _UAPI_LINUX_SUNRPC_NETLINK_H */ diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index f89c10fe7e6a..96727df3aa85 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -14,7 +14,7 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o sysfs.o \ svc_xprt.o \ - xprtmultipath.o + xprtmultipath.o netlink.o sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o sunrpc-$(CONFIG_PROC_FS) += stats.o diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 302bd7ccb39b..391037f15292 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -33,9 +33,11 @@ #include #include #include +#include #include #include "netns.h" +#include "netlink.h" #include "fail.h" #define RPCDBG_FACILITY RPCDBG_CACHE @@ -1963,3 +1965,45 @@ int sunrpc_cache_requests_snapshot(struct cache_detail *cd, return i; } EXPORT_SYMBOL_GPL(sunrpc_cache_requests_snapshot); + +/** + * sunrpc_cache_notify - send a netlink notification for a cache event + * @cd: cache_detail for the cache + * @h: cache_head entry (unused, reserved for future use) + * @cache_type: cache type identifier (e.g. SUNRPC_CACHE_TYPE_UNIX_GID) + * + * Sends a SUNRPC_CMD_CACHE_NOTIFY multicast message on the "exportd" + * group if any listeners are present. Returns 0 on success or a + * negative errno. + */ +int sunrpc_cache_notify(struct cache_detail *cd, struct cache_head *h, + u32 cache_type) +{ + struct genlmsghdr *hdr; + struct sk_buff *msg; + + if (!genl_has_listeners(&sunrpc_nl_family, cd->net, + SUNRPC_NLGRP_EXPORTD)) + return -ENOLINK; + + msg = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &sunrpc_nl_family, 0, + SUNRPC_CMD_CACHE_NOTIFY); + if (!hdr) { + nlmsg_free(msg); + return -ENOMEM; + } + + if (nla_put_u32(msg, SUNRPC_A_CACHE_NOTIFY_CACHE_TYPE, cache_type)) { + nlmsg_free(msg); + return -ENOMEM; + } + + genlmsg_end(msg, hdr); + return genlmsg_multicast_netns(&sunrpc_nl_family, cd->net, msg, 0, + SUNRPC_NLGRP_EXPORTD, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(sunrpc_cache_notify); diff --git a/net/sunrpc/netlink.c b/net/sunrpc/netlink.c new file mode 100644 index 000000000000..952de6de85e3 --- /dev/null +++ b/net/sunrpc/netlink.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/sunrpc_cache.yaml */ +/* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#include +#include +#include + +#include "netlink.h" + +#include + +/* Ops table for sunrpc */ +static const struct genl_split_ops sunrpc_nl_ops[] = { +}; + +static const struct genl_multicast_group sunrpc_nl_mcgrps[] = { + [SUNRPC_NLGRP_NONE] = { "none", }, + [SUNRPC_NLGRP_EXPORTD] = { "exportd", }, +}; + +struct genl_family sunrpc_nl_family __ro_after_init = { + .name = SUNRPC_FAMILY_NAME, + .version = SUNRPC_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = sunrpc_nl_ops, + .n_split_ops = ARRAY_SIZE(sunrpc_nl_ops), + .mcgrps = sunrpc_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(sunrpc_nl_mcgrps), +}; diff --git a/net/sunrpc/netlink.h b/net/sunrpc/netlink.h new file mode 100644 index 000000000000..74cf5183d745 --- /dev/null +++ b/net/sunrpc/netlink.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/sunrpc_cache.yaml */ +/* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _LINUX_SUNRPC_GEN_H +#define _LINUX_SUNRPC_GEN_H + +#include +#include + +#include + +enum { + SUNRPC_NLGRP_NONE, + SUNRPC_NLGRP_EXPORTD, +}; + +extern struct genl_family sunrpc_nl_family; + +#endif /* _LINUX_SUNRPC_GEN_H */ diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index bab6cab29405..ab88ce46afb5 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -23,9 +23,12 @@ #include #include +#include + #include "sunrpc.h" #include "sysfs.h" #include "netns.h" +#include "netlink.h" unsigned int sunrpc_net_id; EXPORT_SYMBOL_GPL(sunrpc_net_id); @@ -108,6 +111,10 @@ init_sunrpc(void) if (err) goto out5; + err = genl_register_family(&sunrpc_nl_family); + if (err) + goto out6; + sunrpc_debugfs_init(); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_register_sysctl(); @@ -116,6 +123,8 @@ init_sunrpc(void) init_socket_xprt(); /* clnt sock transport */ return 0; +out6: + rpc_sysfs_exit(); out5: unregister_rpc_pipefs(); out4: @@ -131,6 +140,7 @@ out: static void __exit cleanup_sunrpc(void) { + genl_unregister_family(&sunrpc_nl_family); rpc_sysfs_exit(); rpc_cleanup_clids(); xprt_cleanup_ids(); -- cgit v1.3-14-g43fede From 712bdbb2153bdb99d4a9d0cdcae24b484610147f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 25 Mar 2026 10:40:29 -0400 Subject: sunrpc: add netlink upcall for the auth.unix.ip cache Add netlink-based cache upcall support for the ip_map (auth.unix.ip) cache, using the sunrpc generic netlink family. Add ip-map attribute-set (seqno, class, addr, domain, negative, expiry), ip-map-reqs wrapper, and ip-map-get-reqs / ip-map-set-reqs operations to the sunrpc_cache YAML spec and generated headers. Implement sunrpc_nl_ip_map_get_reqs_dumpit() which snapshots pending ip_map cache requests and sends each entry's seqno, class name, and IP address over netlink. Implement sunrpc_nl_ip_map_set_reqs_doit() which parses ip_map cache responses from userspace (class, addr, expiry, and domain name or negative flag) and updates the cache via __ip_map_lookup() / __ip_map_update(). Wire up ip_map_notify() callback in ip_map_cache_template so cache misses trigger SUNRPC_CMD_CACHE_NOTIFY multicast events with SUNRPC_CACHE_TYPE_IP_MAP. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/sunrpc_cache.yaml | 47 +++++ include/uapi/linux/sunrpc_netlink.h | 21 +++ net/sunrpc/netlink.c | 34 ++++ net/sunrpc/netlink.h | 8 + net/sunrpc/svcauth_unix.c | 246 ++++++++++++++++++++++++++ 5 files changed, 356 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/sunrpc_cache.yaml b/Documentation/netlink/specs/sunrpc_cache.yaml index f4aa699598bc..8bcd43f65f32 100644 --- a/Documentation/netlink/specs/sunrpc_cache.yaml +++ b/Documentation/netlink/specs/sunrpc_cache.yaml @@ -20,6 +20,35 @@ attribute-sets: name: cache-type type: u32 enum: cache-type + - + name: ip-map + attributes: + - + name: seqno + type: u64 + - + name: class + type: string + - + name: addr + type: string + - + name: domain + type: string + - + name: negative + type: flag + - + name: expiry + type: u64 + - + name: ip-map-reqs + attributes: + - + name: requests + type: nest + nested-attributes: ip-map + multi-attr: true operations: list: @@ -31,6 +60,24 @@ operations: event: attributes: - cache-type + - + name: ip-map-get-reqs + doc: Dump all pending ip_map requests + attribute-set: ip-map-reqs + flags: [admin-perm] + dump: + request: + attributes: + - requests + - + name: ip-map-set-reqs + doc: Respond to one or more ip_map requests + attribute-set: ip-map-reqs + flags: [admin-perm] + do: + request: + attributes: + - requests mcast-groups: list: diff --git a/include/uapi/linux/sunrpc_netlink.h b/include/uapi/linux/sunrpc_netlink.h index 6135d9b3eef1..b44befb5a34b 100644 --- a/include/uapi/linux/sunrpc_netlink.h +++ b/include/uapi/linux/sunrpc_netlink.h @@ -22,8 +22,29 @@ enum { SUNRPC_A_CACHE_NOTIFY_MAX = (__SUNRPC_A_CACHE_NOTIFY_MAX - 1) }; +enum { + SUNRPC_A_IP_MAP_SEQNO = 1, + SUNRPC_A_IP_MAP_CLASS, + SUNRPC_A_IP_MAP_ADDR, + SUNRPC_A_IP_MAP_DOMAIN, + SUNRPC_A_IP_MAP_NEGATIVE, + SUNRPC_A_IP_MAP_EXPIRY, + + __SUNRPC_A_IP_MAP_MAX, + SUNRPC_A_IP_MAP_MAX = (__SUNRPC_A_IP_MAP_MAX - 1) +}; + +enum { + SUNRPC_A_IP_MAP_REQS_REQUESTS = 1, + + __SUNRPC_A_IP_MAP_REQS_MAX, + SUNRPC_A_IP_MAP_REQS_MAX = (__SUNRPC_A_IP_MAP_REQS_MAX - 1) +}; + enum { SUNRPC_CMD_CACHE_NOTIFY = 1, + SUNRPC_CMD_IP_MAP_GET_REQS, + SUNRPC_CMD_IP_MAP_SET_REQS, __SUNRPC_CMD_MAX, SUNRPC_CMD_MAX = (__SUNRPC_CMD_MAX - 1) diff --git a/net/sunrpc/netlink.c b/net/sunrpc/netlink.c index 952de6de85e3..f57eb17fc27d 100644 --- a/net/sunrpc/netlink.c +++ b/net/sunrpc/netlink.c @@ -12,8 +12,42 @@ #include +/* Common nested types */ +const struct nla_policy sunrpc_ip_map_nl_policy[SUNRPC_A_IP_MAP_EXPIRY + 1] = { + [SUNRPC_A_IP_MAP_SEQNO] = { .type = NLA_U64, }, + [SUNRPC_A_IP_MAP_CLASS] = { .type = NLA_NUL_STRING, }, + [SUNRPC_A_IP_MAP_ADDR] = { .type = NLA_NUL_STRING, }, + [SUNRPC_A_IP_MAP_DOMAIN] = { .type = NLA_NUL_STRING, }, + [SUNRPC_A_IP_MAP_NEGATIVE] = { .type = NLA_FLAG, }, + [SUNRPC_A_IP_MAP_EXPIRY] = { .type = NLA_U64, }, +}; + +/* SUNRPC_CMD_IP_MAP_GET_REQS - dump */ +static const struct nla_policy sunrpc_ip_map_get_reqs_nl_policy[SUNRPC_A_IP_MAP_REQS_REQUESTS + 1] = { + [SUNRPC_A_IP_MAP_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_ip_map_nl_policy), +}; + +/* SUNRPC_CMD_IP_MAP_SET_REQS - do */ +static const struct nla_policy sunrpc_ip_map_set_reqs_nl_policy[SUNRPC_A_IP_MAP_REQS_REQUESTS + 1] = { + [SUNRPC_A_IP_MAP_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_ip_map_nl_policy), +}; + /* Ops table for sunrpc */ static const struct genl_split_ops sunrpc_nl_ops[] = { + { + .cmd = SUNRPC_CMD_IP_MAP_GET_REQS, + .dumpit = sunrpc_nl_ip_map_get_reqs_dumpit, + .policy = sunrpc_ip_map_get_reqs_nl_policy, + .maxattr = SUNRPC_A_IP_MAP_REQS_REQUESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = SUNRPC_CMD_IP_MAP_SET_REQS, + .doit = sunrpc_nl_ip_map_set_reqs_doit, + .policy = sunrpc_ip_map_set_reqs_nl_policy, + .maxattr = SUNRPC_A_IP_MAP_REQS_REQUESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group sunrpc_nl_mcgrps[] = { diff --git a/net/sunrpc/netlink.h b/net/sunrpc/netlink.h index 74cf5183d745..68b773960b39 100644 --- a/net/sunrpc/netlink.h +++ b/net/sunrpc/netlink.h @@ -12,6 +12,14 @@ #include +/* Common nested types */ +extern const struct nla_policy sunrpc_ip_map_nl_policy[SUNRPC_A_IP_MAP_EXPIRY + 1]; + +int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int sunrpc_nl_ip_map_set_reqs_doit(struct sk_buff *skb, + struct genl_info *info); + enum { SUNRPC_NLGRP_NONE, SUNRPC_NLGRP_EXPORTD, diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 87732c4cb838..b09b911c532a 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -17,11 +17,14 @@ #include #include #include +#include +#include #include #define RPCDBG_FACILITY RPCDBG_AUTH #include "netns.h" +#include "netlink.h" /* * AUTHUNIX and AUTHNULL credentials are both handled here. @@ -1017,12 +1020,255 @@ struct auth_ops svcauth_unix = { .set_client = svcauth_unix_set_client, }; +static int ip_map_notify(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_notify(cd, h, SUNRPC_CACHE_TYPE_IP_MAP); +} + +/** + * sunrpc_nl_ip_map_get_reqs_dumpit - dump pending ip_map requests + * @skb: reply buffer + * @cb: netlink metadata and command arguments + * + * Walk the ip_map cache's pending request list and create a netlink + * message with a nested entry for each cache_request, containing the + * seqno, class and addr. + * + * Uses cb->args[0] as a seqno cursor for dump continuation across + * multiple netlink messages. + * + * Returns the size of the reply or a negative errno. + */ +int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct sunrpc_net *sn; + struct cache_detail *cd; + struct cache_head **items; + u64 *seqnos; + int cnt, i, emitted; + void *hdr; + int ret; + + sn = net_generic(sock_net(skb->sk), sunrpc_net_id); + + cd = sn->ip_map_cache; + if (!cd) + return -ENODEV; + + cnt = sunrpc_cache_requests_count(cd); + if (!cnt) + return 0; + + items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); + if (!items || !seqnos) { + ret = -ENOMEM; + goto out_alloc; + } + + cnt = sunrpc_cache_requests_snapshot(cd, items, seqnos, cnt, + cb->args[0]); + if (!cnt) { + ret = 0; + goto out_alloc; + } + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &sunrpc_nl_family, + NLM_F_MULTI, SUNRPC_CMD_IP_MAP_GET_REQS); + if (!hdr) { + ret = -ENOBUFS; + goto out_put; + } + + emitted = 0; + for (i = 0; i < cnt; i++) { + struct ip_map *im; + struct nlattr *nest; + char text_addr[40]; + + im = container_of(items[i], struct ip_map, h); + + if (ipv6_addr_v4mapped(&im->m_addr)) + snprintf(text_addr, 20, "%pI4", + &im->m_addr.s6_addr32[3]); + else + snprintf(text_addr, 40, "%pI6", &im->m_addr); + + nest = nla_nest_start(skb, SUNRPC_A_IP_MAP_REQS_REQUESTS); + if (!nest) + break; + + if (nla_put_u64_64bit(skb, SUNRPC_A_IP_MAP_SEQNO, + seqnos[i], 0) || + nla_put_string(skb, SUNRPC_A_IP_MAP_CLASS, + im->m_class) || + nla_put_string(skb, SUNRPC_A_IP_MAP_ADDR, text_addr)) { + nla_nest_cancel(skb, nest); + break; + } + + nla_nest_end(skb, nest); + cb->args[0] = seqnos[i]; + emitted++; + } + + if (!emitted) { + genlmsg_cancel(skb, hdr); + ret = -EMSGSIZE; + goto out_put; + } + + genlmsg_end(skb, hdr); + ret = skb->len; +out_put: + for (i = 0; i < cnt; i++) + cache_put(items[i], cd); +out_alloc: + kfree(seqnos); + kfree(items); + return ret; +} + +/** + * sunrpc_nl_parse_one_ip_map - parse one ip_map entry from netlink + * @cd: cache_detail for the ip_map cache + * @attr: nested attribute containing ip_map fields + * + * Parses one ip_map entry from a netlink message and updates the + * cache. Mirrors the logic in ip_map_parse(). + * + * Returns 0 on success or a negative errno. + */ +static int sunrpc_nl_parse_one_ip_map(struct cache_detail *cd, + struct nlattr *attr) +{ + struct nlattr *tb[SUNRPC_A_IP_MAP_EXPIRY + 1]; + union { + struct sockaddr sa; + struct sockaddr_in s4; + struct sockaddr_in6 s6; + } address; + struct sockaddr_in6 sin6; + struct ip_map *ipmp; + struct auth_domain *dom = NULL; + struct unix_domain *udom = NULL; + struct timespec64 boot; + time64_t expiry; + char class[8]; + int err; + int len; + + err = nla_parse_nested(tb, SUNRPC_A_IP_MAP_EXPIRY, attr, + sunrpc_ip_map_nl_policy, NULL); + if (err) + return err; + + /* class (required) */ + if (!tb[SUNRPC_A_IP_MAP_CLASS]) + return -EINVAL; + len = nla_len(tb[SUNRPC_A_IP_MAP_CLASS]); + if (len <= 0 || len > sizeof(class)) + return -EINVAL; + nla_strscpy(class, tb[SUNRPC_A_IP_MAP_CLASS], sizeof(class)); + + /* addr (required) */ + if (!tb[SUNRPC_A_IP_MAP_ADDR]) + return -EINVAL; + if (rpc_pton(cd->net, nla_data(tb[SUNRPC_A_IP_MAP_ADDR]), + nla_len(tb[SUNRPC_A_IP_MAP_ADDR]) - 1, + &address.sa, sizeof(address)) == 0) + return -EINVAL; + + switch (address.sa.sa_family) { + case AF_INET: + sin6.sin6_family = AF_INET6; + ipv6_addr_set_v4mapped(address.s4.sin_addr.s_addr, + &sin6.sin6_addr); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + memcpy(&sin6, &address.s6, sizeof(sin6)); + break; +#endif + default: + return -EINVAL; + } + + /* expiry (required, wallclock seconds) */ + if (!tb[SUNRPC_A_IP_MAP_EXPIRY]) + return -EINVAL; + getboottime64(&boot); + expiry = nla_get_u64(tb[SUNRPC_A_IP_MAP_EXPIRY]) - boot.tv_sec; + + /* domain name or negative */ + if (tb[SUNRPC_A_IP_MAP_NEGATIVE]) { + udom = NULL; + } else if (tb[SUNRPC_A_IP_MAP_DOMAIN]) { + dom = unix_domain_find(nla_data(tb[SUNRPC_A_IP_MAP_DOMAIN])); + if (!dom) + return -ENOENT; + udom = container_of(dom, struct unix_domain, h); + } else { + return -EINVAL; + } + + ipmp = __ip_map_lookup(cd, class, &sin6.sin6_addr); + if (ipmp) + err = __ip_map_update(cd, ipmp, udom, expiry); + else + err = -ENOMEM; + + if (dom) + auth_domain_put(dom); + + cache_flush(); + return err; +} + +/** + * sunrpc_nl_ip_map_set_reqs_doit - respond to ip_map requests + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Parse one or more ip_map cache responses from userspace and + * update the ip_map cache accordingly. + * + * Returns 0 on success or a negative errno. + */ +int sunrpc_nl_ip_map_set_reqs_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct sunrpc_net *sn; + struct cache_detail *cd; + const struct nlattr *attr; + int rem, ret = 0; + + sn = net_generic(genl_info_net(info), sunrpc_net_id); + + cd = sn->ip_map_cache; + if (!cd) + return -ENODEV; + + nlmsg_for_each_attr_type(attr, SUNRPC_A_IP_MAP_REQS_REQUESTS, + info->nlhdr, GENL_HDRLEN, rem) { + ret = sunrpc_nl_parse_one_ip_map(cd, + (struct nlattr *)attr); + if (ret) + break; + } + + return ret; +} + static const struct cache_detail ip_map_cache_template = { .owner = THIS_MODULE, .hash_size = IP_HASHMAX, .name = "auth.unix.ip", .cache_put = ip_map_put, .cache_upcall = ip_map_upcall, + .cache_notify = ip_map_notify, .cache_request = ip_map_request, .cache_parse = ip_map_parse, .cache_show = ip_map_show, -- cgit v1.3-14-g43fede From 0850e8603cd7a3a17e2888391937154a54b93e02 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 25 Mar 2026 10:40:30 -0400 Subject: sunrpc: add netlink upcall for the auth.unix.gid cache Add netlink-based cache upcall support for the unix_gid (auth.unix.gid) cache, using the sunrpc generic netlink family. Add unix-gid attribute-set (seqno, uid, gids multi-attr, negative, expiry), unix-gid-reqs wrapper, and unix-gid-get-reqs / unix-gid-set-reqs operations to the sunrpc_cache YAML spec and generated headers. Implement sunrpc_nl_unix_gid_get_reqs_dumpit() which snapshots pending unix_gid cache requests and sends each entry's seqno and uid over netlink. Implement sunrpc_nl_unix_gid_set_reqs_doit() which parses unix_gid cache responses from userspace (uid, expiry, gids as u32 multi-attr or negative flag) and updates the cache via unix_gid_lookup() / sunrpc_cache_update(). Wire up unix_gid_notify() callback in unix_gid_cache_template so cache misses trigger SUNRPC_CMD_CACHE_NOTIFY multicast events with SUNRPC_CACHE_TYPE_UNIX_GID. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/sunrpc_cache.yaml | 45 +++++ include/uapi/linux/sunrpc_netlink.h | 20 +++ net/sunrpc/netlink.c | 32 ++++ net/sunrpc/netlink.h | 5 + net/sunrpc/svcauth_unix.c | 234 ++++++++++++++++++++++++++ 5 files changed, 336 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/sunrpc_cache.yaml b/Documentation/netlink/specs/sunrpc_cache.yaml index 8bcd43f65f32..ed0ddb61ebcf 100644 --- a/Documentation/netlink/specs/sunrpc_cache.yaml +++ b/Documentation/netlink/specs/sunrpc_cache.yaml @@ -49,6 +49,33 @@ attribute-sets: type: nest nested-attributes: ip-map multi-attr: true + - + name: unix-gid + attributes: + - + name: seqno + type: u64 + - + name: uid + type: u32 + - + name: gids + type: u32 + multi-attr: true + - + name: negative + type: flag + - + name: expiry + type: u64 + - + name: unix-gid-reqs + attributes: + - + name: requests + type: nest + nested-attributes: unix-gid + multi-attr: true operations: list: @@ -78,6 +105,24 @@ operations: request: attributes: - requests + - + name: unix-gid-get-reqs + doc: Dump all pending unix_gid requests + attribute-set: unix-gid-reqs + flags: [admin-perm] + dump: + request: + attributes: + - requests + - + name: unix-gid-set-reqs + doc: Respond to one or more unix_gid requests + attribute-set: unix-gid-reqs + flags: [admin-perm] + do: + request: + attributes: + - requests mcast-groups: list: diff --git a/include/uapi/linux/sunrpc_netlink.h b/include/uapi/linux/sunrpc_netlink.h index b44befb5a34b..d71c623e92ab 100644 --- a/include/uapi/linux/sunrpc_netlink.h +++ b/include/uapi/linux/sunrpc_netlink.h @@ -41,10 +41,30 @@ enum { SUNRPC_A_IP_MAP_REQS_MAX = (__SUNRPC_A_IP_MAP_REQS_MAX - 1) }; +enum { + SUNRPC_A_UNIX_GID_SEQNO = 1, + SUNRPC_A_UNIX_GID_UID, + SUNRPC_A_UNIX_GID_GIDS, + SUNRPC_A_UNIX_GID_NEGATIVE, + SUNRPC_A_UNIX_GID_EXPIRY, + + __SUNRPC_A_UNIX_GID_MAX, + SUNRPC_A_UNIX_GID_MAX = (__SUNRPC_A_UNIX_GID_MAX - 1) +}; + +enum { + SUNRPC_A_UNIX_GID_REQS_REQUESTS = 1, + + __SUNRPC_A_UNIX_GID_REQS_MAX, + SUNRPC_A_UNIX_GID_REQS_MAX = (__SUNRPC_A_UNIX_GID_REQS_MAX - 1) +}; + enum { SUNRPC_CMD_CACHE_NOTIFY = 1, SUNRPC_CMD_IP_MAP_GET_REQS, SUNRPC_CMD_IP_MAP_SET_REQS, + SUNRPC_CMD_UNIX_GID_GET_REQS, + SUNRPC_CMD_UNIX_GID_SET_REQS, __SUNRPC_CMD_MAX, SUNRPC_CMD_MAX = (__SUNRPC_CMD_MAX - 1) diff --git a/net/sunrpc/netlink.c b/net/sunrpc/netlink.c index f57eb17fc27d..41843f007c37 100644 --- a/net/sunrpc/netlink.c +++ b/net/sunrpc/netlink.c @@ -32,6 +32,24 @@ static const struct nla_policy sunrpc_ip_map_set_reqs_nl_policy[SUNRPC_A_IP_MAP_ [SUNRPC_A_IP_MAP_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_ip_map_nl_policy), }; +const struct nla_policy sunrpc_unix_gid_nl_policy[SUNRPC_A_UNIX_GID_EXPIRY + 1] = { + [SUNRPC_A_UNIX_GID_SEQNO] = { .type = NLA_U64, }, + [SUNRPC_A_UNIX_GID_UID] = { .type = NLA_U32, }, + [SUNRPC_A_UNIX_GID_GIDS] = { .type = NLA_U32, }, + [SUNRPC_A_UNIX_GID_NEGATIVE] = { .type = NLA_FLAG, }, + [SUNRPC_A_UNIX_GID_EXPIRY] = { .type = NLA_U64, }, +}; + +/* SUNRPC_CMD_UNIX_GID_GET_REQS - dump */ +static const struct nla_policy sunrpc_unix_gid_get_reqs_nl_policy[SUNRPC_A_UNIX_GID_REQS_REQUESTS + 1] = { + [SUNRPC_A_UNIX_GID_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_unix_gid_nl_policy), +}; + +/* SUNRPC_CMD_UNIX_GID_SET_REQS - do */ +static const struct nla_policy sunrpc_unix_gid_set_reqs_nl_policy[SUNRPC_A_UNIX_GID_REQS_REQUESTS + 1] = { + [SUNRPC_A_UNIX_GID_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_unix_gid_nl_policy), +}; + /* Ops table for sunrpc */ static const struct genl_split_ops sunrpc_nl_ops[] = { { @@ -48,6 +66,20 @@ static const struct genl_split_ops sunrpc_nl_ops[] = { .maxattr = SUNRPC_A_IP_MAP_REQS_REQUESTS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = SUNRPC_CMD_UNIX_GID_GET_REQS, + .dumpit = sunrpc_nl_unix_gid_get_reqs_dumpit, + .policy = sunrpc_unix_gid_get_reqs_nl_policy, + .maxattr = SUNRPC_A_UNIX_GID_REQS_REQUESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = SUNRPC_CMD_UNIX_GID_SET_REQS, + .doit = sunrpc_nl_unix_gid_set_reqs_doit, + .policy = sunrpc_unix_gid_set_reqs_nl_policy, + .maxattr = SUNRPC_A_UNIX_GID_REQS_REQUESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group sunrpc_nl_mcgrps[] = { diff --git a/net/sunrpc/netlink.h b/net/sunrpc/netlink.h index 68b773960b39..16b87519a409 100644 --- a/net/sunrpc/netlink.h +++ b/net/sunrpc/netlink.h @@ -14,11 +14,16 @@ /* Common nested types */ extern const struct nla_policy sunrpc_ip_map_nl_policy[SUNRPC_A_IP_MAP_EXPIRY + 1]; +extern const struct nla_policy sunrpc_unix_gid_nl_policy[SUNRPC_A_UNIX_GID_EXPIRY + 1]; int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int sunrpc_nl_ip_map_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); +int sunrpc_nl_unix_gid_get_reqs_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int sunrpc_nl_unix_gid_set_reqs_doit(struct sk_buff *skb, + struct genl_info *info); enum { SUNRPC_NLGRP_NONE, diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index b09b911c532a..7703523d4246 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -585,12 +585,246 @@ static int unix_gid_show(struct seq_file *m, return 0; } +static int unix_gid_notify(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_notify(cd, h, SUNRPC_CACHE_TYPE_UNIX_GID); +} + +/** + * sunrpc_nl_unix_gid_get_reqs_dumpit - dump pending unix_gid requests + * @skb: reply buffer + * @cb: netlink metadata and command arguments + * + * Walk the unix_gid cache's pending request list and create a netlink + * message with a nested entry for each cache_request, containing the + * seqno and uid. + * + * Uses cb->args[0] as a seqno cursor for dump continuation across + * multiple netlink messages. + * + * Returns the size of the reply or a negative errno. + */ +int sunrpc_nl_unix_gid_get_reqs_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct sunrpc_net *sn; + struct cache_detail *cd; + struct cache_head **items; + u64 *seqnos; + int cnt, i, emitted; + void *hdr; + int ret; + + sn = net_generic(sock_net(skb->sk), sunrpc_net_id); + + cd = sn->unix_gid_cache; + if (!cd) + return -ENODEV; + + cnt = sunrpc_cache_requests_count(cd); + if (!cnt) + return 0; + + items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); + if (!items || !seqnos) { + ret = -ENOMEM; + goto out_alloc; + } + + cnt = sunrpc_cache_requests_snapshot(cd, items, seqnos, cnt, + cb->args[0]); + if (!cnt) { + ret = 0; + goto out_alloc; + } + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &sunrpc_nl_family, + NLM_F_MULTI, SUNRPC_CMD_UNIX_GID_GET_REQS); + if (!hdr) { + ret = -ENOBUFS; + goto out_put; + } + + emitted = 0; + for (i = 0; i < cnt; i++) { + struct unix_gid *ug; + struct nlattr *nest; + + ug = container_of(items[i], struct unix_gid, h); + + nest = nla_nest_start(skb, + SUNRPC_A_UNIX_GID_REQS_REQUESTS); + if (!nest) + break; + + if (nla_put_u64_64bit(skb, SUNRPC_A_UNIX_GID_SEQNO, + seqnos[i], 0) || + nla_put_u32(skb, SUNRPC_A_UNIX_GID_UID, + from_kuid(&init_user_ns, ug->uid))) { + nla_nest_cancel(skb, nest); + break; + } + + nla_nest_end(skb, nest); + cb->args[0] = seqnos[i]; + emitted++; + } + + if (!emitted) { + genlmsg_cancel(skb, hdr); + ret = -EMSGSIZE; + goto out_put; + } + + genlmsg_end(skb, hdr); + ret = skb->len; +out_put: + for (i = 0; i < cnt; i++) + cache_put(items[i], cd); +out_alloc: + kfree(seqnos); + kfree(items); + return ret; +} + +/** + * sunrpc_nl_parse_one_unix_gid - parse one unix_gid entry from netlink + * @cd: cache_detail for the unix_gid cache + * @attr: nested attribute containing unix_gid fields + * + * Parses one unix_gid entry from a netlink message and updates the + * cache. Mirrors the logic in unix_gid_parse(). + * + * Returns 0 on success or a negative errno. + */ +static int sunrpc_nl_parse_one_unix_gid(struct cache_detail *cd, + struct nlattr *attr) +{ + struct nlattr *tb[SUNRPC_A_UNIX_GID_EXPIRY + 1]; + struct unix_gid ug, *ugp; + struct timespec64 boot; + struct nlattr *gid_attr; + int err, rem, gids = 0; + kuid_t uid; + + err = nla_parse_nested(tb, SUNRPC_A_UNIX_GID_EXPIRY, attr, + sunrpc_unix_gid_nl_policy, NULL); + if (err) + return err; + + /* uid (required) */ + if (!tb[SUNRPC_A_UNIX_GID_UID]) + return -EINVAL; + uid = make_kuid(current_user_ns(), + nla_get_u32(tb[SUNRPC_A_UNIX_GID_UID])); + ug.uid = uid; + + /* expiry (required, wallclock seconds) */ + if (!tb[SUNRPC_A_UNIX_GID_EXPIRY]) + return -EINVAL; + getboottime64(&boot); + ug.h.flags = 0; + ug.h.expiry_time = nla_get_u64(tb[SUNRPC_A_UNIX_GID_EXPIRY]) - + boot.tv_sec; + + if (tb[SUNRPC_A_UNIX_GID_NEGATIVE]) { + ug.gi = groups_alloc(0); + if (!ug.gi) + return -ENOMEM; + } else { + /* Count gids */ + nla_for_each_nested_type(gid_attr, SUNRPC_A_UNIX_GID_GIDS, + attr, rem) + gids++; + + if (gids > 8192) + return -EINVAL; + + ug.gi = groups_alloc(gids); + if (!ug.gi) + return -ENOMEM; + + gids = 0; + nla_for_each_nested_type(gid_attr, SUNRPC_A_UNIX_GID_GIDS, + attr, rem) { + kgid_t kgid; + + kgid = make_kgid(current_user_ns(), + nla_get_u32(gid_attr)); + if (!gid_valid(kgid)) { + err = -EINVAL; + goto out; + } + ug.gi->gid[gids++] = kgid; + } + groups_sort(ug.gi); + } + + ugp = unix_gid_lookup(cd, uid); + if (ugp) { + struct cache_head *ch; + + ch = sunrpc_cache_update(cd, &ug.h, &ugp->h, + unix_gid_hash(uid)); + if (!ch) { + err = -ENOMEM; + } else { + err = 0; + cache_put(ch, cd); + } + } else { + err = -ENOMEM; + } +out: + if (ug.gi) + put_group_info(ug.gi); + return err; +} + +/** + * sunrpc_nl_unix_gid_set_reqs_doit - respond to unix_gid requests + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Parse one or more unix_gid cache responses from userspace and + * update the unix_gid cache accordingly. + * + * Returns 0 on success or a negative errno. + */ +int sunrpc_nl_unix_gid_set_reqs_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct sunrpc_net *sn; + struct cache_detail *cd; + const struct nlattr *attr; + int rem, ret = 0; + + sn = net_generic(genl_info_net(info), sunrpc_net_id); + + cd = sn->unix_gid_cache; + if (!cd) + return -ENODEV; + + nlmsg_for_each_attr_type(attr, SUNRPC_A_UNIX_GID_REQS_REQUESTS, + info->nlhdr, GENL_HDRLEN, rem) { + ret = sunrpc_nl_parse_one_unix_gid(cd, + (struct nlattr *)attr); + if (ret) + break; + } + + return ret; +} + static const struct cache_detail unix_gid_cache_template = { .owner = THIS_MODULE, .hash_size = GID_HASHMAX, .name = "auth.unix.gid", .cache_put = unix_gid_put, .cache_upcall = unix_gid_upcall, + .cache_notify = unix_gid_notify, .cache_request = unix_gid_request, .cache_parse = unix_gid_parse, .cache_show = unix_gid_show, -- cgit v1.3-14-g43fede From 912fc994b920a24543725d981e9cd082d1376ed7 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 25 Mar 2026 10:40:31 -0400 Subject: nfsd: add netlink upcall for the svc_export cache Add netlink-based cache upcall support for the svc_export (nfsd.export) cache to Documentation/netlink/specs/nfsd.yaml and regenerate the resulting files. Implement nfsd_cache_notify() which sends a NFSD_CMD_CACHE_NOTIFY multicast event to the "exportd" group, carrying the cache type so userspace knows which cache has pending requests. Implement nfsd_nl_svc_export_get_reqs_dumpit() which snapshots pending svc_export cache requests and sends each entry's seqno, client name, and path over netlink. Implement nfsd_nl_svc_export_set_reqs_doit() which parses svc_export cache responses from userspace (client, path, expiry, flags, anon uid/gid, fslocations, uuid, secinfo, xprtsec, fsid, or negative flag) and updates the cache via svc_export_lookup() / svc_export_update(). Wire up the svc_export_notify() callback in svc_export_cache_template so cache misses trigger NFSD_CMD_CACHE_NOTIFY multicast events with NFSD_CACHE_TYPE_SVC_EXPORT. Note that the export-flags and xprtsec-mode enums are organized to match their counterparts in include/uapi/linux/nfsd/export.h. The intent is that future export options will only be added to the netlink headers, which should eliminate the need to keep so much in sync. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 162 +++++++++++++ fs/nfsd/export.c | 444 +++++++++++++++++++++++++++++++++- fs/nfsd/netlink.c | 61 +++++ fs/nfsd/netlink.h | 13 + fs/nfsd/nfsctl.c | 28 +++ fs/nfsd/nfsd.h | 2 +- include/uapi/linux/nfsd_netlink.h | 101 ++++++++ net/sunrpc/netlink.c | 17 +- net/sunrpc/netlink.h | 3 +- 9 files changed, 815 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 8ab43c8253b2..9ba1cf348b40 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -6,7 +6,51 @@ uapi-header: linux/nfsd_netlink.h doc: NFSD configuration over generic netlink. +definitions: + - + type: flags + name: cache-type + entries: [svc_export] + - + type: flags + name: export-flags + doc: These flags are ordered to match the NFSEXP_* flags in include/linux/nfsd/export.h + entries: + - readonly + - insecure-port + - rootsquash + - allsquash + - async + - gathered-writes + - noreaddirplus + - security-label + - sign-fh + - nohide + - nosubtreecheck + - noauthnlm + - msnfs + - fsid + - crossmount + - noacl + - v4root + - pnfs + - + type: flags + name: xprtsec-mode + doc: These flags are ordered to match the NFSEXP_XPRTSEC_* flags in include/linux/nfsd/export.h + entries: + - none + - tls + - mtls + attribute-sets: + - + name: cache-notify + attributes: + - + name: cache-type + type: u32 + enum: cache-type - name: rpc-status attributes: @@ -132,6 +176,91 @@ attribute-sets: - name: npools type: u32 + - + name: fslocation + attributes: + - + name: host + type: string + - + name: path + type: string + - + name: fslocations + attributes: + - + name: location + type: nest + nested-attributes: fslocation + multi-attr: true + - + name: auth-flavor + attributes: + - + name: pseudoflavor + type: u32 + - + name: flags + type: u32 + enum: export-flags + enum-as-flags: true + - + name: svc-export + attributes: + - + name: seqno + type: u64 + - + name: client + type: string + - + name: path + type: string + - + name: negative + type: flag + - + name: expiry + type: u64 + - + name: anon-uid + type: u32 + - + name: anon-gid + type: u32 + - + name: fslocations + type: nest + nested-attributes: fslocations + - + name: uuid + type: binary + - + name: secinfo + type: nest + nested-attributes: auth-flavor + multi-attr: true + - + name: xprtsec + type: u32 + enum: xprtsec-mode + multi-attr: true + - + name: flags + type: u32 + enum: export-flags + enum-as-flags: true + - + name: fsid + type: s32 + - + name: svc-export-reqs + attributes: + - + name: requests + type: nest + nested-attributes: svc-export + multi-attr: true operations: list: @@ -233,3 +362,36 @@ operations: attributes: - mode - npools + - + name: cache-notify + doc: Notification that there are cache requests that need servicing + attribute-set: cache-notify + mcgrp: exportd + event: + attributes: + - cache-type + - + name: svc-export-get-reqs + doc: Dump all pending svc_export requests + attribute-set: svc-export-reqs + flags: [admin-perm] + dump: + request: + attributes: + - requests + - + name: svc-export-set-reqs + doc: Respond to one or more svc_export requests + attribute-set: svc-export-reqs + flags: [admin-perm] + do: + request: + attributes: + - requests + +mcast-groups: + list: + - + name: none + - + name: exportd diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index adc2266ea9f2..79bfa7a7087a 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -17,6 +17,8 @@ #include #include #include +#include +#include #include "nfsd.h" #include "nfsfh.h" @@ -24,6 +26,7 @@ #include "pnfs.h" #include "filecache.h" #include "trace.h" +#include "netlink.h" #define NFSDDBG_FACILITY NFSDDBG_EXPORT @@ -386,11 +389,447 @@ static void svc_export_put(struct kref *ref) queue_rcu_work(nfsd_export_wq, &exp->ex_rwork); } +/** + * nfsd_nl_svc_export_get_reqs_dumpit - dump pending svc_export requests + * @skb: reply buffer + * @cb: netlink metadata and command arguments + * + * Walk the svc_export cache's pending request list and create a netlink + * message with a nested entry for each cache_request, containing the + * seqno, client string, and path. + * + * Uses cb->args[0] as a seqno cursor for dump continuation across + * multiple netlink messages. + * + * Returns the size of the reply or a negative errno. + */ +int nfsd_nl_svc_export_get_reqs_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nfsd_net *nn; + struct cache_detail *cd; + struct cache_head **items; + u64 *seqnos; + int cnt, i, emitted; + char *pathbuf; + void *hdr; + int ret; + + nn = net_generic(sock_net(skb->sk), nfsd_net_id); + + mutex_lock(&nfsd_mutex); + + cd = nn->svc_export_cache; + if (!cd) { + ret = -ENODEV; + goto out_unlock; + } + + cnt = sunrpc_cache_requests_count(cd); + if (!cnt) { + ret = 0; + goto out_unlock; + } + + items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!items || !seqnos || !pathbuf) { + ret = -ENOMEM; + goto out_alloc; + } + + cnt = sunrpc_cache_requests_snapshot(cd, items, seqnos, cnt, + cb->args[0]); + if (!cnt) { + ret = 0; + goto out_alloc; + } + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &nfsd_nl_family, + NLM_F_MULTI, NFSD_CMD_SVC_EXPORT_GET_REQS); + if (!hdr) { + ret = -ENOBUFS; + goto out_put; + } + + emitted = 0; + for (i = 0; i < cnt; i++) { + struct svc_export *exp; + struct nlattr *nest; + char *pth; + + exp = container_of(items[i], struct svc_export, h); + + pth = d_path(&exp->ex_path, pathbuf, PATH_MAX); + if (IS_ERR(pth)) + continue; + + nest = nla_nest_start(skb, + NFSD_A_SVC_EXPORT_REQS_REQUESTS); + if (!nest) + break; + + if (nla_put_u64_64bit(skb, NFSD_A_SVC_EXPORT_SEQNO, + seqnos[i], 0) || + nla_put_string(skb, NFSD_A_SVC_EXPORT_CLIENT, + exp->ex_client->name) || + nla_put_string(skb, NFSD_A_SVC_EXPORT_PATH, pth)) { + nla_nest_cancel(skb, nest); + break; + } + + nla_nest_end(skb, nest); + cb->args[0] = seqnos[i]; + emitted++; + } + + if (!emitted) { + genlmsg_cancel(skb, hdr); + ret = -EMSGSIZE; + goto out_put; + } + + genlmsg_end(skb, hdr); + ret = skb->len; +out_put: + for (i = 0; i < cnt; i++) + cache_put(items[i], cd); +out_alloc: + kfree(pathbuf); + kfree(seqnos); + kfree(items); +out_unlock: + mutex_unlock(&nfsd_mutex); + return ret; +} + +/** + * nfsd_nl_parse_fslocations - parse fslocations from netlink + * @attr: NFSD_A_SVC_EXPORT_FSLOCATIONS nested attribute + * @fsloc: fslocations struct to fill in + * + * Returns 0 on success or a negative errno. + */ +static int nfsd_nl_parse_fslocations(struct nlattr *attr, + struct nfsd4_fs_locations *fsloc) +{ + struct nlattr *loc_attr; + int rem, count = 0; + int err; + + if (fsloc->locations) + return -EINVAL; + + /* Count locations first */ + nla_for_each_nested_type(loc_attr, NFSD_A_FSLOCATIONS_LOCATION, + attr, rem) + count++; + + if (count > MAX_FS_LOCATIONS) + return -EINVAL; + if (!count) + return 0; + + fsloc->locations = kcalloc(count, sizeof(struct nfsd4_fs_location), + GFP_KERNEL); + if (!fsloc->locations) + return -ENOMEM; + + nla_for_each_nested_type(loc_attr, NFSD_A_FSLOCATIONS_LOCATION, + attr, rem) { + struct nlattr *tb[NFSD_A_FSLOCATION_PATH + 1]; + struct nfsd4_fs_location *loc; + + err = nla_parse_nested(tb, NFSD_A_FSLOCATION_PATH, loc_attr, + nfsd_fslocation_nl_policy, NULL); + if (err) + goto out_free; + + if (!tb[NFSD_A_FSLOCATION_HOST] || + !tb[NFSD_A_FSLOCATION_PATH]) { + err = -EINVAL; + goto out_free; + } + + loc = &fsloc->locations[fsloc->locations_count++]; + loc->hosts = kstrdup(nla_data(tb[NFSD_A_FSLOCATION_HOST]), + GFP_KERNEL); + loc->path = kstrdup(nla_data(tb[NFSD_A_FSLOCATION_PATH]), + GFP_KERNEL); + if (!loc->hosts || !loc->path) { + err = -ENOMEM; + goto out_free; + } + } + + return 0; +out_free: + nfsd4_fslocs_free(fsloc); + return err; +} + +static struct svc_export *svc_export_update(struct svc_export *new, + struct svc_export *old); +static struct svc_export *svc_export_lookup(struct svc_export *); +static int check_export(const struct path *path, int *flags, + unsigned char *uuid); + +/** + * nfsd_nl_parse_one_export - parse one svc_export entry from a netlink message + * @cd: cache_detail for the svc_export cache + * @attr: nested attribute containing svc-export fields + * + * Parses one svc-export entry from a netlink message and updates the + * cache. Mirrors the logic in svc_export_parse(). + * + * Returns 0 on success or a negative errno. + */ +static int nfsd_nl_parse_one_export(struct cache_detail *cd, + struct nlattr *attr) +{ + struct nlattr *tb[NFSD_A_SVC_EXPORT_FSID + 1]; + struct auth_domain *dom = NULL; + struct svc_export exp = {}, *expp; + struct nlattr *secinfo_attr; + struct timespec64 boot; + int err, rem; + + err = nla_parse_nested(tb, NFSD_A_SVC_EXPORT_FSID, attr, + nfsd_svc_export_nl_policy, NULL); + if (err) + return err; + + /* client (required) */ + if (!tb[NFSD_A_SVC_EXPORT_CLIENT]) + return -EINVAL; + + dom = auth_domain_find(nla_data(tb[NFSD_A_SVC_EXPORT_CLIENT])); + if (!dom) + return -ENOENT; + + /* path (required) */ + if (!tb[NFSD_A_SVC_EXPORT_PATH]) { + err = -EINVAL; + goto out_dom; + } + + err = kern_path(nla_data(tb[NFSD_A_SVC_EXPORT_PATH]), 0, + &exp.ex_path); + if (err) + goto out_dom; + + exp.ex_client = dom; + exp.cd = cd; + exp.ex_devid_map = NULL; + exp.ex_xprtsec_modes = NFSEXP_XPRTSEC_ALL; + + /* expiry (required, wallclock seconds) */ + if (!tb[NFSD_A_SVC_EXPORT_EXPIRY]) { + err = -EINVAL; + goto out_path; + } + getboottime64(&boot); + exp.h.expiry_time = nla_get_u64(tb[NFSD_A_SVC_EXPORT_EXPIRY]) - + boot.tv_sec; + + if (tb[NFSD_A_SVC_EXPORT_NEGATIVE]) { + set_bit(CACHE_NEGATIVE, &exp.h.flags); + } else { + /* flags */ + if (tb[NFSD_A_SVC_EXPORT_FLAGS]) + exp.ex_flags = nla_get_u32(tb[NFSD_A_SVC_EXPORT_FLAGS]); + + /* anon uid */ + if (tb[NFSD_A_SVC_EXPORT_ANON_UID]) { + u32 uid = nla_get_u32(tb[NFSD_A_SVC_EXPORT_ANON_UID]); + + exp.ex_anon_uid = make_kuid(current_user_ns(), uid); + } + + /* anon gid */ + if (tb[NFSD_A_SVC_EXPORT_ANON_GID]) { + u32 gid = nla_get_u32(tb[NFSD_A_SVC_EXPORT_ANON_GID]); + + exp.ex_anon_gid = make_kgid(current_user_ns(), gid); + } + + /* fsid */ + if (tb[NFSD_A_SVC_EXPORT_FSID]) + exp.ex_fsid = nla_get_s32(tb[NFSD_A_SVC_EXPORT_FSID]); + + /* fslocations */ + if (tb[NFSD_A_SVC_EXPORT_FSLOCATIONS]) { + struct nlattr *fsl = tb[NFSD_A_SVC_EXPORT_FSLOCATIONS]; + + err = nfsd_nl_parse_fslocations(fsl, + &exp.ex_fslocs); + if (err) + goto out_path; + } + + /* uuid */ + if (tb[NFSD_A_SVC_EXPORT_UUID]) { + if (nla_len(tb[NFSD_A_SVC_EXPORT_UUID]) != + EX_UUID_LEN) { + err = -EINVAL; + goto out_fslocs; + } + exp.ex_uuid = kmemdup(nla_data(tb[NFSD_A_SVC_EXPORT_UUID]), + EX_UUID_LEN, GFP_KERNEL); + if (!exp.ex_uuid) { + err = -ENOMEM; + goto out_fslocs; + } + } + + /* secinfo (multi-attr) */ + nla_for_each_nested_type(secinfo_attr, + NFSD_A_SVC_EXPORT_SECINFO, + attr, rem) { + struct nlattr *ftb[NFSD_A_AUTH_FLAVOR_FLAGS + 1]; + struct exp_flavor_info *f; + + if (exp.ex_nflavors >= MAX_SECINFO_LIST) { + err = -EINVAL; + goto out_uuid; + } + + err = nla_parse_nested(ftb, + NFSD_A_AUTH_FLAVOR_FLAGS, + secinfo_attr, + nfsd_auth_flavor_nl_policy, + NULL); + if (err) + goto out_uuid; + + f = &exp.ex_flavors[exp.ex_nflavors++]; + + if (ftb[NFSD_A_AUTH_FLAVOR_PSEUDOFLAVOR]) + f->pseudoflavor = nla_get_u32(ftb[NFSD_A_AUTH_FLAVOR_PSEUDOFLAVOR]); + + if (ftb[NFSD_A_AUTH_FLAVOR_FLAGS]) + f->flags = nla_get_u32(ftb[NFSD_A_AUTH_FLAVOR_FLAGS]); + + /* Only some flags are allowed to differ between flavors: */ + if (~NFSEXP_SECINFO_FLAGS & (f->flags ^ exp.ex_flags)) { + err = -EINVAL; + goto out_uuid; + } + } + + /* xprtsec (multi-attr u32) */ + if (tb[NFSD_A_SVC_EXPORT_XPRTSEC]) { + struct nlattr *xp_attr; + + exp.ex_xprtsec_modes = 0; + nla_for_each_nested_type(xp_attr, + NFSD_A_SVC_EXPORT_XPRTSEC, + attr, rem) { + u32 mode = nla_get_u32(xp_attr); + + if (mode > NFSEXP_XPRTSEC_MTLS) { + err = -EINVAL; + goto out_uuid; + } + exp.ex_xprtsec_modes |= mode; + } + } + + err = check_export(&exp.ex_path, &exp.ex_flags, + exp.ex_uuid); + if (err) + goto out_uuid; + + if (exp.h.expiry_time < seconds_since_boot()) + goto out_uuid; + + err = -EINVAL; + if (!uid_valid(exp.ex_anon_uid)) + goto out_uuid; + if (!gid_valid(exp.ex_anon_gid)) + goto out_uuid; + err = 0; + + nfsd4_setup_layout_type(&exp); + } + + expp = svc_export_lookup(&exp); + if (!expp) { + err = -ENOMEM; + goto out_uuid; + } + expp = svc_export_update(&exp, expp); + if (expp) { + trace_nfsd_export_update(expp); + cache_flush(); + exp_put(expp); + } else { + err = -ENOMEM; + } + +out_uuid: + kfree(exp.ex_uuid); +out_fslocs: + nfsd4_fslocs_free(&exp.ex_fslocs); +out_path: + path_put(&exp.ex_path); +out_dom: + auth_domain_put(dom); + return err; +} + +/** + * nfsd_nl_svc_export_set_reqs_doit - respond to svc_export requests + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Parse one or more svc_export cache responses from userspace and + * update the export cache accordingly. + * + * Returns 0 on success or a negative errno. + */ +int nfsd_nl_svc_export_set_reqs_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct nfsd_net *nn; + struct cache_detail *cd; + const struct nlattr *attr; + int rem, ret = 0; + + nn = net_generic(genl_info_net(info), nfsd_net_id); + + mutex_lock(&nfsd_mutex); + + cd = nn->svc_export_cache; + if (!cd) { + ret = -ENODEV; + goto out_unlock; + } + + nlmsg_for_each_attr_type(attr, NFSD_A_SVC_EXPORT_REQS_REQUESTS, + info->nlhdr, GENL_HDRLEN, rem) { + ret = nfsd_nl_parse_one_export(cd, (struct nlattr *)attr); + if (ret) + break; + } + +out_unlock: + mutex_unlock(&nfsd_mutex); + return ret; +} + static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_upcall(cd, h); } +static int svc_export_notify(struct cache_detail *cd, struct cache_head *h) +{ + return nfsd_cache_notify(cd, h, NFSD_CACHE_TYPE_SVC_EXPORT); +} + static void svc_export_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) @@ -410,10 +849,6 @@ static void svc_export_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } -static struct svc_export *svc_export_update(struct svc_export *new, - struct svc_export *old); -static struct svc_export *svc_export_lookup(struct svc_export *); - static int check_export(const struct path *path, int *flags, unsigned char *uuid) { struct inode *inode = d_inode(path->dentry); @@ -908,6 +1343,7 @@ static const struct cache_detail svc_export_cache_template = { .name = "nfsd.export", .cache_put = svc_export_put, .cache_upcall = svc_export_upcall, + .cache_notify = svc_export_notify, .cache_request = svc_export_request, .cache_parse = svc_export_parse, .cache_show = svc_export_show, diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index 81c943345d13..fb401d7302af 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -12,11 +12,41 @@ #include /* Common nested types */ +const struct nla_policy nfsd_auth_flavor_nl_policy[NFSD_A_AUTH_FLAVOR_FLAGS + 1] = { + [NFSD_A_AUTH_FLAVOR_PSEUDOFLAVOR] = { .type = NLA_U32, }, + [NFSD_A_AUTH_FLAVOR_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0x3ffff), +}; + +const struct nla_policy nfsd_fslocation_nl_policy[NFSD_A_FSLOCATION_PATH + 1] = { + [NFSD_A_FSLOCATION_HOST] = { .type = NLA_NUL_STRING, }, + [NFSD_A_FSLOCATION_PATH] = { .type = NLA_NUL_STRING, }, +}; + +const struct nla_policy nfsd_fslocations_nl_policy[NFSD_A_FSLOCATIONS_LOCATION + 1] = { + [NFSD_A_FSLOCATIONS_LOCATION] = NLA_POLICY_NESTED(nfsd_fslocation_nl_policy), +}; + const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1] = { [NFSD_A_SOCK_ADDR] = { .type = NLA_BINARY, }, [NFSD_A_SOCK_TRANSPORT_NAME] = { .type = NLA_NUL_STRING, }, }; +const struct nla_policy nfsd_svc_export_nl_policy[NFSD_A_SVC_EXPORT_FSID + 1] = { + [NFSD_A_SVC_EXPORT_SEQNO] = { .type = NLA_U64, }, + [NFSD_A_SVC_EXPORT_CLIENT] = { .type = NLA_NUL_STRING, }, + [NFSD_A_SVC_EXPORT_PATH] = { .type = NLA_NUL_STRING, }, + [NFSD_A_SVC_EXPORT_NEGATIVE] = { .type = NLA_FLAG, }, + [NFSD_A_SVC_EXPORT_EXPIRY] = { .type = NLA_U64, }, + [NFSD_A_SVC_EXPORT_ANON_UID] = { .type = NLA_U32, }, + [NFSD_A_SVC_EXPORT_ANON_GID] = { .type = NLA_U32, }, + [NFSD_A_SVC_EXPORT_FSLOCATIONS] = NLA_POLICY_NESTED(nfsd_fslocations_nl_policy), + [NFSD_A_SVC_EXPORT_UUID] = { .type = NLA_BINARY, }, + [NFSD_A_SVC_EXPORT_SECINFO] = NLA_POLICY_NESTED(nfsd_auth_flavor_nl_policy), + [NFSD_A_SVC_EXPORT_XPRTSEC] = NLA_POLICY_MASK(NLA_U32, 0x7), + [NFSD_A_SVC_EXPORT_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0x3ffff), + [NFSD_A_SVC_EXPORT_FSID] = { .type = NLA_S32, }, +}; + const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1] = { [NFSD_A_VERSION_MAJOR] = { .type = NLA_U32, }, [NFSD_A_VERSION_MINOR] = { .type = NLA_U32, }, @@ -48,6 +78,16 @@ static const struct nla_policy nfsd_pool_mode_set_nl_policy[NFSD_A_POOL_MODE_MOD [NFSD_A_POOL_MODE_MODE] = { .type = NLA_NUL_STRING, }, }; +/* NFSD_CMD_SVC_EXPORT_GET_REQS - dump */ +static const struct nla_policy nfsd_svc_export_get_reqs_nl_policy[NFSD_A_SVC_EXPORT_REQS_REQUESTS + 1] = { + [NFSD_A_SVC_EXPORT_REQS_REQUESTS] = NLA_POLICY_NESTED(nfsd_svc_export_nl_policy), +}; + +/* NFSD_CMD_SVC_EXPORT_SET_REQS - do */ +static const struct nla_policy nfsd_svc_export_set_reqs_nl_policy[NFSD_A_SVC_EXPORT_REQS_REQUESTS + 1] = { + [NFSD_A_SVC_EXPORT_REQS_REQUESTS] = NLA_POLICY_NESTED(nfsd_svc_export_nl_policy), +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -103,6 +143,25 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .doit = nfsd_nl_pool_mode_get_doit, .flags = GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_SVC_EXPORT_GET_REQS, + .dumpit = nfsd_nl_svc_export_get_reqs_dumpit, + .policy = nfsd_svc_export_get_reqs_nl_policy, + .maxattr = NFSD_A_SVC_EXPORT_REQS_REQUESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = NFSD_CMD_SVC_EXPORT_SET_REQS, + .doit = nfsd_nl_svc_export_set_reqs_doit, + .policy = nfsd_svc_export_set_reqs_nl_policy, + .maxattr = NFSD_A_SVC_EXPORT_REQS_REQUESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, +}; + +static const struct genl_multicast_group nfsd_nl_mcgrps[] = { + [NFSD_NLGRP_NONE] = { "none", }, + [NFSD_NLGRP_EXPORTD] = { "exportd", }, }; struct genl_family nfsd_nl_family __ro_after_init = { @@ -113,4 +172,6 @@ struct genl_family nfsd_nl_family __ro_after_init = { .module = THIS_MODULE, .split_ops = nfsd_nl_ops, .n_split_ops = ARRAY_SIZE(nfsd_nl_ops), + .mcgrps = nfsd_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(nfsd_nl_mcgrps), }; diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index 478117ff6b8c..d6ed8d9b0bb1 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -13,7 +13,11 @@ #include /* Common nested types */ +extern const struct nla_policy nfsd_auth_flavor_nl_policy[NFSD_A_AUTH_FLAVOR_FLAGS + 1]; +extern const struct nla_policy nfsd_fslocation_nl_policy[NFSD_A_FSLOCATION_PATH + 1]; +extern const struct nla_policy nfsd_fslocations_nl_policy[NFSD_A_FSLOCATIONS_LOCATION + 1]; extern const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1]; +extern const struct nla_policy nfsd_svc_export_nl_policy[NFSD_A_SVC_EXPORT_FSID + 1]; extern const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1]; int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, @@ -26,6 +30,15 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_svc_export_get_reqs_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int nfsd_nl_svc_export_set_reqs_doit(struct sk_buff *skb, + struct genl_info *info); + +enum { + NFSD_NLGRP_NONE, + NFSD_NLGRP_EXPORTD, +}; extern struct genl_family nfsd_nl_family; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index a457ed836972..c93cf82e3647 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2212,6 +2212,34 @@ err_free_msg: return err; } +int nfsd_cache_notify(struct cache_detail *cd, struct cache_head *h, u32 cache_type) +{ + struct genlmsghdr *hdr; + struct sk_buff *msg; + + if (!genl_has_listeners(&nfsd_nl_family, cd->net, NFSD_NLGRP_EXPORTD)) + return -ENOLINK; + + msg = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfsd_nl_family, 0, NFSD_CMD_CACHE_NOTIFY); + if (!hdr) { + nlmsg_free(msg); + return -ENOMEM; + } + + if (nla_put_u32(msg, NFSD_A_CACHE_NOTIFY_CACHE_TYPE, cache_type)) { + nlmsg_free(msg); + return -ENOMEM; + } + + genlmsg_end(msg, hdr); + return genlmsg_multicast_netns(&nfsd_nl_family, cd->net, msg, 0, + NFSD_NLGRP_EXPORTD, GFP_KERNEL); +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 260bf8badb03..709da3c7a5fa 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -108,7 +108,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, const struct tree_descr *, struct dentry **fdentries); void nfsd_client_rmdir(struct dentry *dentry); - +int nfsd_cache_notify(struct cache_detail *cd, struct cache_head *h, u32 cache_type); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 97c7447f4d14..32a551b320e0 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -10,6 +10,52 @@ #define NFSD_FAMILY_NAME "nfsd" #define NFSD_FAMILY_VERSION 1 +enum nfsd_cache_type { + NFSD_CACHE_TYPE_SVC_EXPORT = 1, +}; + +/* + * These flags are ordered to match the NFSEXP_* flags in + * include/linux/nfsd/export.h + */ +enum nfsd_export_flags { + NFSD_EXPORT_FLAGS_READONLY = 1, + NFSD_EXPORT_FLAGS_INSECURE_PORT = 2, + NFSD_EXPORT_FLAGS_ROOTSQUASH = 4, + NFSD_EXPORT_FLAGS_ALLSQUASH = 8, + NFSD_EXPORT_FLAGS_ASYNC = 16, + NFSD_EXPORT_FLAGS_GATHERED_WRITES = 32, + NFSD_EXPORT_FLAGS_NOREADDIRPLUS = 64, + NFSD_EXPORT_FLAGS_SECURITY_LABEL = 128, + NFSD_EXPORT_FLAGS_SIGN_FH = 256, + NFSD_EXPORT_FLAGS_NOHIDE = 512, + NFSD_EXPORT_FLAGS_NOSUBTREECHECK = 1024, + NFSD_EXPORT_FLAGS_NOAUTHNLM = 2048, + NFSD_EXPORT_FLAGS_MSNFS = 4096, + NFSD_EXPORT_FLAGS_FSID = 8192, + NFSD_EXPORT_FLAGS_CROSSMOUNT = 16384, + NFSD_EXPORT_FLAGS_NOACL = 32768, + NFSD_EXPORT_FLAGS_V4ROOT = 65536, + NFSD_EXPORT_FLAGS_PNFS = 131072, +}; + +/* + * These flags are ordered to match the NFSEXP_XPRTSEC_* flags in + * include/linux/nfsd/export.h + */ +enum nfsd_xprtsec_mode { + NFSD_XPRTSEC_MODE_NONE = 1, + NFSD_XPRTSEC_MODE_TLS = 2, + NFSD_XPRTSEC_MODE_MTLS = 4, +}; + +enum { + NFSD_A_CACHE_NOTIFY_CACHE_TYPE = 1, + + __NFSD_A_CACHE_NOTIFY_MAX, + NFSD_A_CACHE_NOTIFY_MAX = (__NFSD_A_CACHE_NOTIFY_MAX - 1) +}; + enum { NFSD_A_RPC_STATUS_XID = 1, NFSD_A_RPC_STATUS_FLAGS, @@ -81,6 +127,55 @@ enum { NFSD_A_POOL_MODE_MAX = (__NFSD_A_POOL_MODE_MAX - 1) }; +enum { + NFSD_A_FSLOCATION_HOST = 1, + NFSD_A_FSLOCATION_PATH, + + __NFSD_A_FSLOCATION_MAX, + NFSD_A_FSLOCATION_MAX = (__NFSD_A_FSLOCATION_MAX - 1) +}; + +enum { + NFSD_A_FSLOCATIONS_LOCATION = 1, + + __NFSD_A_FSLOCATIONS_MAX, + NFSD_A_FSLOCATIONS_MAX = (__NFSD_A_FSLOCATIONS_MAX - 1) +}; + +enum { + NFSD_A_AUTH_FLAVOR_PSEUDOFLAVOR = 1, + NFSD_A_AUTH_FLAVOR_FLAGS, + + __NFSD_A_AUTH_FLAVOR_MAX, + NFSD_A_AUTH_FLAVOR_MAX = (__NFSD_A_AUTH_FLAVOR_MAX - 1) +}; + +enum { + NFSD_A_SVC_EXPORT_SEQNO = 1, + NFSD_A_SVC_EXPORT_CLIENT, + NFSD_A_SVC_EXPORT_PATH, + NFSD_A_SVC_EXPORT_NEGATIVE, + NFSD_A_SVC_EXPORT_EXPIRY, + NFSD_A_SVC_EXPORT_ANON_UID, + NFSD_A_SVC_EXPORT_ANON_GID, + NFSD_A_SVC_EXPORT_FSLOCATIONS, + NFSD_A_SVC_EXPORT_UUID, + NFSD_A_SVC_EXPORT_SECINFO, + NFSD_A_SVC_EXPORT_XPRTSEC, + NFSD_A_SVC_EXPORT_FLAGS, + NFSD_A_SVC_EXPORT_FSID, + + __NFSD_A_SVC_EXPORT_MAX, + NFSD_A_SVC_EXPORT_MAX = (__NFSD_A_SVC_EXPORT_MAX - 1) +}; + +enum { + NFSD_A_SVC_EXPORT_REQS_REQUESTS = 1, + + __NFSD_A_SVC_EXPORT_REQS_MAX, + NFSD_A_SVC_EXPORT_REQS_MAX = (__NFSD_A_SVC_EXPORT_REQS_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, @@ -91,9 +186,15 @@ enum { NFSD_CMD_LISTENER_GET, NFSD_CMD_POOL_MODE_SET, NFSD_CMD_POOL_MODE_GET, + NFSD_CMD_CACHE_NOTIFY, + NFSD_CMD_SVC_EXPORT_GET_REQS, + NFSD_CMD_SVC_EXPORT_SET_REQS, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) }; +#define NFSD_MCGRP_NONE "none" +#define NFSD_MCGRP_EXPORTD "exportd" + #endif /* _UAPI_LINUX_NFSD_NETLINK_H */ diff --git a/net/sunrpc/netlink.c b/net/sunrpc/netlink.c index 41843f007c37..3ac6b0cac5fe 100644 --- a/net/sunrpc/netlink.c +++ b/net/sunrpc/netlink.c @@ -6,7 +6,6 @@ #include #include -#include #include "netlink.h" @@ -22,6 +21,14 @@ const struct nla_policy sunrpc_ip_map_nl_policy[SUNRPC_A_IP_MAP_EXPIRY + 1] = { [SUNRPC_A_IP_MAP_EXPIRY] = { .type = NLA_U64, }, }; +const struct nla_policy sunrpc_unix_gid_nl_policy[SUNRPC_A_UNIX_GID_EXPIRY + 1] = { + [SUNRPC_A_UNIX_GID_SEQNO] = { .type = NLA_U64, }, + [SUNRPC_A_UNIX_GID_UID] = { .type = NLA_U32, }, + [SUNRPC_A_UNIX_GID_GIDS] = { .type = NLA_U32, }, + [SUNRPC_A_UNIX_GID_NEGATIVE] = { .type = NLA_FLAG, }, + [SUNRPC_A_UNIX_GID_EXPIRY] = { .type = NLA_U64, }, +}; + /* SUNRPC_CMD_IP_MAP_GET_REQS - dump */ static const struct nla_policy sunrpc_ip_map_get_reqs_nl_policy[SUNRPC_A_IP_MAP_REQS_REQUESTS + 1] = { [SUNRPC_A_IP_MAP_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_ip_map_nl_policy), @@ -32,14 +39,6 @@ static const struct nla_policy sunrpc_ip_map_set_reqs_nl_policy[SUNRPC_A_IP_MAP_ [SUNRPC_A_IP_MAP_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_ip_map_nl_policy), }; -const struct nla_policy sunrpc_unix_gid_nl_policy[SUNRPC_A_UNIX_GID_EXPIRY + 1] = { - [SUNRPC_A_UNIX_GID_SEQNO] = { .type = NLA_U64, }, - [SUNRPC_A_UNIX_GID_UID] = { .type = NLA_U32, }, - [SUNRPC_A_UNIX_GID_GIDS] = { .type = NLA_U32, }, - [SUNRPC_A_UNIX_GID_NEGATIVE] = { .type = NLA_FLAG, }, - [SUNRPC_A_UNIX_GID_EXPIRY] = { .type = NLA_U64, }, -}; - /* SUNRPC_CMD_UNIX_GID_GET_REQS - dump */ static const struct nla_policy sunrpc_unix_gid_get_reqs_nl_policy[SUNRPC_A_UNIX_GID_REQS_REQUESTS + 1] = { [SUNRPC_A_UNIX_GID_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_unix_gid_nl_policy), diff --git a/net/sunrpc/netlink.h b/net/sunrpc/netlink.h index 16b87519a409..2aec57d27a58 100644 --- a/net/sunrpc/netlink.h +++ b/net/sunrpc/netlink.h @@ -18,8 +18,7 @@ extern const struct nla_policy sunrpc_unix_gid_nl_policy[SUNRPC_A_UNIX_GID_EXPIR int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb); -int sunrpc_nl_ip_map_set_reqs_doit(struct sk_buff *skb, - struct genl_info *info); +int sunrpc_nl_ip_map_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); int sunrpc_nl_unix_gid_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int sunrpc_nl_unix_gid_set_reqs_doit(struct sk_buff *skb, -- cgit v1.3-14-g43fede From 01c2305795a3b6b164df48e72b12022a68fd60c1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 25 Mar 2026 10:40:32 -0400 Subject: nfsd: add netlink upcall for the nfsd.fh cache Add netlink-based cache upcall support for the expkey (nfsd.fh) cache, following the same pattern as the existing svc_export netlink support. Add expkey to the cache-type enum, a new expkey attribute-set with client, fsidtype, fsid, negative, expiry, and path fields, and the expkey-get-reqs / expkey-set-reqs operations to the nfsd YAML spec and generated headers. Implement nfsd_nl_expkey_get_reqs_dumpit() which snapshots pending expkey cache requests and sends each entry's seqno, client name, fsidtype, and fsid over netlink. Implement nfsd_nl_expkey_set_reqs_doit() which parses expkey cache responses from userspace (client, fsidtype, fsid, expiry, and path or negative flag) and updates the cache via svc_expkey_lookup() / svc_expkey_update(). Wire up the expkey_notify() callback in svc_expkey_cache_template so cache misses trigger NFSD_CMD_CACHE_NOTIFY multicast events with NFSD_CACHE_TYPE_EXPKEY. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 52 ++++++- fs/nfsd/export.c | 266 ++++++++++++++++++++++++++++++++++ fs/nfsd/netlink.c | 34 +++++ fs/nfsd/netlink.h | 4 + include/uapi/linux/nfsd_netlink.h | 23 +++ 5 files changed, 378 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 9ba1cf348b40..7030b40273fd 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -10,7 +10,7 @@ definitions: - type: flags name: cache-type - entries: [svc_export] + entries: [svc_export, expkey] - type: flags name: export-flags @@ -261,6 +261,38 @@ attribute-sets: type: nest nested-attributes: svc-export multi-attr: true + - + name: expkey + attributes: + - + name: seqno + type: u64 + - + name: client + type: string + - + name: fsidtype + type: u8 + - + name: fsid + type: binary + - + name: negative + type: flag + - + name: expiry + type: u64 + - + name: path + type: string + - + name: expkey-reqs + attributes: + - + name: requests + type: nest + nested-attributes: expkey + multi-attr: true operations: list: @@ -388,6 +420,24 @@ operations: request: attributes: - requests + - + name: expkey-get-reqs + doc: Dump all pending expkey requests + attribute-set: expkey-reqs + flags: [admin-perm] + dump: + request: + attributes: + - requests + - + name: expkey-set-reqs + doc: Respond to one or more expkey requests + attribute-set: expkey-reqs + flags: [admin-perm] + do: + request: + attributes: + - requests mcast-groups: list: diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 79bfa7a7087a..eb020054f9a3 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -266,12 +266,18 @@ static void expkey_flush(void) mutex_unlock(&nfsd_mutex); } +static int expkey_notify(struct cache_detail *cd, struct cache_head *h) +{ + return nfsd_cache_notify(cd, h, NFSD_CACHE_TYPE_EXPKEY); +} + static const struct cache_detail svc_expkey_cache_template = { .owner = THIS_MODULE, .hash_size = EXPKEY_HASHMAX, .name = "nfsd.fh", .cache_put = expkey_put, .cache_upcall = expkey_upcall, + .cache_notify = expkey_notify, .cache_request = expkey_request, .cache_parse = expkey_parse, .cache_show = expkey_show, @@ -322,6 +328,266 @@ svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new, return NULL; } +/** + * nfsd_nl_expkey_get_reqs_dumpit - dump pending expkey requests + * @skb: reply buffer + * @cb: netlink metadata and command arguments + * + * Walk the expkey cache's pending request list and create a netlink + * message with a nested entry for each cache_request, containing the + * seqno, client string, fsidtype and fsid. + * + * Uses cb->args[0] as a seqno cursor for dump continuation across + * multiple netlink messages. + * + * Returns the size of the reply or a negative errno. + */ +int nfsd_nl_expkey_get_reqs_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nfsd_net *nn; + struct cache_detail *cd; + struct cache_head **items; + u64 *seqnos; + int cnt, i, emitted; + void *hdr; + int ret; + + nn = net_generic(sock_net(skb->sk), nfsd_net_id); + + mutex_lock(&nfsd_mutex); + + cd = nn->svc_expkey_cache; + if (!cd) { + ret = -ENODEV; + goto out_unlock; + } + + cnt = sunrpc_cache_requests_count(cd); + if (!cnt) { + ret = 0; + goto out_unlock; + } + + items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); + if (!items || !seqnos) { + ret = -ENOMEM; + goto out_alloc; + } + + cnt = sunrpc_cache_requests_snapshot(cd, items, seqnos, cnt, + cb->args[0]); + if (!cnt) { + ret = 0; + goto out_alloc; + } + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &nfsd_nl_family, + NLM_F_MULTI, NFSD_CMD_EXPKEY_GET_REQS); + if (!hdr) { + ret = -ENOBUFS; + goto out_put; + } + + emitted = 0; + for (i = 0; i < cnt; i++) { + struct svc_expkey *ek; + struct nlattr *nest; + + ek = container_of(items[i], struct svc_expkey, h); + + nest = nla_nest_start(skb, NFSD_A_EXPKEY_REQS_REQUESTS); + if (!nest) + break; + + if (nla_put_u64_64bit(skb, NFSD_A_EXPKEY_SEQNO, + seqnos[i], 0) || + nla_put_string(skb, NFSD_A_EXPKEY_CLIENT, + ek->ek_client->name) || + nla_put_u8(skb, NFSD_A_EXPKEY_FSIDTYPE, + ek->ek_fsidtype) || + nla_put(skb, NFSD_A_EXPKEY_FSID, + key_len(ek->ek_fsidtype), ek->ek_fsid)) { + nla_nest_cancel(skb, nest); + break; + } + + nla_nest_end(skb, nest); + cb->args[0] = seqnos[i]; + emitted++; + } + + if (!emitted) { + genlmsg_cancel(skb, hdr); + ret = -EMSGSIZE; + goto out_put; + } + + genlmsg_end(skb, hdr); + ret = skb->len; +out_put: + for (i = 0; i < cnt; i++) + cache_put(items[i], cd); +out_alloc: + kfree(seqnos); + kfree(items); +out_unlock: + mutex_unlock(&nfsd_mutex); + return ret; +} + +/** + * nfsd_nl_parse_one_expkey - parse one expkey entry from netlink + * @cd: cache_detail for the expkey cache + * @attr: nested attribute containing expkey fields + * + * Parses one expkey entry from a netlink message and updates the + * cache. Mirrors the logic in expkey_parse(). + * + * Returns 0 on success or a negative errno. + */ +static int nfsd_nl_parse_one_expkey(struct cache_detail *cd, + struct nlattr *attr) +{ + struct nlattr *tb[NFSD_A_EXPKEY_PATH + 1]; + struct auth_domain *dom = NULL; + struct svc_expkey key; + struct svc_expkey *ek = NULL; + struct timespec64 boot; + int err; + u8 fsidtype; + int fsid_len; + + err = nla_parse_nested(tb, NFSD_A_EXPKEY_PATH, attr, + nfsd_expkey_nl_policy, NULL); + if (err) + return err; + + /* client (required) */ + if (!tb[NFSD_A_EXPKEY_CLIENT]) + return -EINVAL; + + dom = auth_domain_find(nla_data(tb[NFSD_A_EXPKEY_CLIENT])); + if (!dom) + return -ENOENT; + + /* fsidtype (required) */ + if (!tb[NFSD_A_EXPKEY_FSIDTYPE]) { + err = -EINVAL; + goto out_dom; + } + fsidtype = nla_get_u8(tb[NFSD_A_EXPKEY_FSIDTYPE]); + if (key_len(fsidtype) == 0) { + err = -EINVAL; + goto out_dom; + } + + /* fsid (required) */ + if (!tb[NFSD_A_EXPKEY_FSID]) { + err = -EINVAL; + goto out_dom; + } + fsid_len = nla_len(tb[NFSD_A_EXPKEY_FSID]); + if (fsid_len != key_len(fsidtype)) { + err = -EINVAL; + goto out_dom; + } + + /* expiry (required, wallclock seconds) */ + if (!tb[NFSD_A_EXPKEY_EXPIRY]) { + err = -EINVAL; + goto out_dom; + } + + key.h.flags = 0; + getboottime64(&boot); + key.h.expiry_time = nla_get_u64(tb[NFSD_A_EXPKEY_EXPIRY]) - + boot.tv_sec; + key.ek_client = dom; + key.ek_fsidtype = fsidtype; + memcpy(key.ek_fsid, nla_data(tb[NFSD_A_EXPKEY_FSID]), fsid_len); + + ek = svc_expkey_lookup(cd, &key); + if (!ek) { + err = -ENOMEM; + goto out_dom; + } + + if (tb[NFSD_A_EXPKEY_NEGATIVE]) { + set_bit(CACHE_NEGATIVE, &key.h.flags); + ek = svc_expkey_update(cd, &key, ek); + if (ek) + trace_nfsd_expkey_update(ek, NULL); + else + err = -ENOMEM; + } else if (tb[NFSD_A_EXPKEY_PATH]) { + err = kern_path(nla_data(tb[NFSD_A_EXPKEY_PATH]), 0, + &key.ek_path); + if (err) + goto out_ek; + ek = svc_expkey_update(cd, &key, ek); + if (ek) + trace_nfsd_expkey_update(ek, + nla_data(tb[NFSD_A_EXPKEY_PATH])); + else + err = -ENOMEM; + path_put(&key.ek_path); + } else { + err = -EINVAL; + goto out_ek; + } + + cache_flush(); + +out_ek: + if (ek) + cache_put(&ek->h, cd); +out_dom: + auth_domain_put(dom); + return err; +} + +/** + * nfsd_nl_expkey_set_reqs_doit - respond to expkey requests + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Parse one or more expkey cache responses from userspace and + * update the expkey cache accordingly. + * + * Returns 0 on success or a negative errno. + */ +int nfsd_nl_expkey_set_reqs_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct nfsd_net *nn; + struct cache_detail *cd; + const struct nlattr *attr; + int rem, ret = 0; + + nn = net_generic(genl_info_net(info), nfsd_net_id); + + mutex_lock(&nfsd_mutex); + + cd = nn->svc_expkey_cache; + if (!cd) { + ret = -ENODEV; + goto out_unlock; + } + + nlmsg_for_each_attr_type(attr, NFSD_A_EXPKEY_REQS_REQUESTS, + info->nlhdr, GENL_HDRLEN, rem) { + ret = nfsd_nl_parse_one_expkey(cd, (struct nlattr *)attr); + if (ret) + break; + } + +out_unlock: + mutex_unlock(&nfsd_mutex); + return ret; +} #define EXPORT_HASHBITS 8 #define EXPORT_HASHMAX (1<< EXPORT_HASHBITS) diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index fb401d7302af..394230e250a5 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -17,6 +17,16 @@ const struct nla_policy nfsd_auth_flavor_nl_policy[NFSD_A_AUTH_FLAVOR_FLAGS + 1] [NFSD_A_AUTH_FLAVOR_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0x3ffff), }; +const struct nla_policy nfsd_expkey_nl_policy[NFSD_A_EXPKEY_PATH + 1] = { + [NFSD_A_EXPKEY_SEQNO] = { .type = NLA_U64, }, + [NFSD_A_EXPKEY_CLIENT] = { .type = NLA_NUL_STRING, }, + [NFSD_A_EXPKEY_FSIDTYPE] = { .type = NLA_U8, }, + [NFSD_A_EXPKEY_FSID] = { .type = NLA_BINARY, }, + [NFSD_A_EXPKEY_NEGATIVE] = { .type = NLA_FLAG, }, + [NFSD_A_EXPKEY_EXPIRY] = { .type = NLA_U64, }, + [NFSD_A_EXPKEY_PATH] = { .type = NLA_NUL_STRING, }, +}; + const struct nla_policy nfsd_fslocation_nl_policy[NFSD_A_FSLOCATION_PATH + 1] = { [NFSD_A_FSLOCATION_HOST] = { .type = NLA_NUL_STRING, }, [NFSD_A_FSLOCATION_PATH] = { .type = NLA_NUL_STRING, }, @@ -88,6 +98,16 @@ static const struct nla_policy nfsd_svc_export_set_reqs_nl_policy[NFSD_A_SVC_EXP [NFSD_A_SVC_EXPORT_REQS_REQUESTS] = NLA_POLICY_NESTED(nfsd_svc_export_nl_policy), }; +/* NFSD_CMD_EXPKEY_GET_REQS - dump */ +static const struct nla_policy nfsd_expkey_get_reqs_nl_policy[NFSD_A_EXPKEY_REQS_REQUESTS + 1] = { + [NFSD_A_EXPKEY_REQS_REQUESTS] = NLA_POLICY_NESTED(nfsd_expkey_nl_policy), +}; + +/* NFSD_CMD_EXPKEY_SET_REQS - do */ +static const struct nla_policy nfsd_expkey_set_reqs_nl_policy[NFSD_A_EXPKEY_REQS_REQUESTS + 1] = { + [NFSD_A_EXPKEY_REQS_REQUESTS] = NLA_POLICY_NESTED(nfsd_expkey_nl_policy), +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -157,6 +177,20 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .maxattr = NFSD_A_SVC_EXPORT_REQS_REQUESTS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_EXPKEY_GET_REQS, + .dumpit = nfsd_nl_expkey_get_reqs_dumpit, + .policy = nfsd_expkey_get_reqs_nl_policy, + .maxattr = NFSD_A_EXPKEY_REQS_REQUESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = NFSD_CMD_EXPKEY_SET_REQS, + .doit = nfsd_nl_expkey_set_reqs_doit, + .policy = nfsd_expkey_set_reqs_nl_policy, + .maxattr = NFSD_A_EXPKEY_REQS_REQUESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group nfsd_nl_mcgrps[] = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index d6ed8d9b0bb1..f5b338777285 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -14,6 +14,7 @@ /* Common nested types */ extern const struct nla_policy nfsd_auth_flavor_nl_policy[NFSD_A_AUTH_FLAVOR_FLAGS + 1]; +extern const struct nla_policy nfsd_expkey_nl_policy[NFSD_A_EXPKEY_PATH + 1]; extern const struct nla_policy nfsd_fslocation_nl_policy[NFSD_A_FSLOCATION_PATH + 1]; extern const struct nla_policy nfsd_fslocations_nl_policy[NFSD_A_FSLOCATIONS_LOCATION + 1]; extern const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1]; @@ -34,6 +35,9 @@ int nfsd_nl_svc_export_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int nfsd_nl_svc_export_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_expkey_get_reqs_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int nfsd_nl_expkey_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); enum { NFSD_NLGRP_NONE, diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 32a551b320e0..fed7533c1533 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -12,6 +12,7 @@ enum nfsd_cache_type { NFSD_CACHE_TYPE_SVC_EXPORT = 1, + NFSD_CACHE_TYPE_EXPKEY = 2, }; /* @@ -176,6 +177,26 @@ enum { NFSD_A_SVC_EXPORT_REQS_MAX = (__NFSD_A_SVC_EXPORT_REQS_MAX - 1) }; +enum { + NFSD_A_EXPKEY_SEQNO = 1, + NFSD_A_EXPKEY_CLIENT, + NFSD_A_EXPKEY_FSIDTYPE, + NFSD_A_EXPKEY_FSID, + NFSD_A_EXPKEY_NEGATIVE, + NFSD_A_EXPKEY_EXPIRY, + NFSD_A_EXPKEY_PATH, + + __NFSD_A_EXPKEY_MAX, + NFSD_A_EXPKEY_MAX = (__NFSD_A_EXPKEY_MAX - 1) +}; + +enum { + NFSD_A_EXPKEY_REQS_REQUESTS = 1, + + __NFSD_A_EXPKEY_REQS_MAX, + NFSD_A_EXPKEY_REQS_MAX = (__NFSD_A_EXPKEY_REQS_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, @@ -189,6 +210,8 @@ enum { NFSD_CMD_CACHE_NOTIFY, NFSD_CMD_SVC_EXPORT_GET_REQS, NFSD_CMD_SVC_EXPORT_SET_REQS, + NFSD_CMD_EXPKEY_GET_REQS, + NFSD_CMD_EXPKEY_SET_REQS, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.3-14-g43fede From 565ee23ea2374a0ec42bb70227447baa81fcd196 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 25 Mar 2026 10:40:33 -0400 Subject: sunrpc: add SUNRPC_CMD_CACHE_FLUSH netlink command Add a new SUNRPC_CMD_CACHE_FLUSH generic netlink command that allows userspace to flush the sunrpc auth caches (ip_map and unix_gid) without writing to /proc/net/rpc/*/flush. An optional SUNRPC_A_CACHE_FLUSH_MASK u32 attribute selects which caches to flush (bit 1 = ip_map, bit 2 = unix_gid). If the attribute is omitted, all sunrpc caches are flushed. This is used by exportfs to replace its /proc-based cache_flush() with a netlink equivalent, with /proc fallback for older kernels. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/sunrpc_cache.yaml | 17 ++++++++++++++ include/uapi/linux/sunrpc_netlink.h | 8 +++++++ net/sunrpc/netlink.c | 12 ++++++++++ net/sunrpc/netlink.h | 1 + net/sunrpc/svcauth_unix.c | 32 +++++++++++++++++++++++++++ 5 files changed, 70 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/sunrpc_cache.yaml b/Documentation/netlink/specs/sunrpc_cache.yaml index ed0ddb61ebcf..55dabc914dbc 100644 --- a/Documentation/netlink/specs/sunrpc_cache.yaml +++ b/Documentation/netlink/specs/sunrpc_cache.yaml @@ -76,6 +76,14 @@ attribute-sets: type: nest nested-attributes: unix-gid multi-attr: true + - + name: cache-flush + attributes: + - + name: mask + type: u32 + enum: cache-type + enum-as-flags: true operations: list: @@ -123,6 +131,15 @@ operations: request: attributes: - requests + - + name: cache-flush + doc: Flush sunrpc caches (ip_map and/or unix_gid) + attribute-set: cache-flush + flags: [admin-perm] + do: + request: + attributes: + - mask mcast-groups: list: diff --git a/include/uapi/linux/sunrpc_netlink.h b/include/uapi/linux/sunrpc_netlink.h index d71c623e92ab..34677f0ec2f9 100644 --- a/include/uapi/linux/sunrpc_netlink.h +++ b/include/uapi/linux/sunrpc_netlink.h @@ -59,12 +59,20 @@ enum { SUNRPC_A_UNIX_GID_REQS_MAX = (__SUNRPC_A_UNIX_GID_REQS_MAX - 1) }; +enum { + SUNRPC_A_CACHE_FLUSH_MASK = 1, + + __SUNRPC_A_CACHE_FLUSH_MAX, + SUNRPC_A_CACHE_FLUSH_MAX = (__SUNRPC_A_CACHE_FLUSH_MAX - 1) +}; + enum { SUNRPC_CMD_CACHE_NOTIFY = 1, SUNRPC_CMD_IP_MAP_GET_REQS, SUNRPC_CMD_IP_MAP_SET_REQS, SUNRPC_CMD_UNIX_GID_GET_REQS, SUNRPC_CMD_UNIX_GID_SET_REQS, + SUNRPC_CMD_CACHE_FLUSH, __SUNRPC_CMD_MAX, SUNRPC_CMD_MAX = (__SUNRPC_CMD_MAX - 1) diff --git a/net/sunrpc/netlink.c b/net/sunrpc/netlink.c index 3ac6b0cac5fe..5ccf0967809c 100644 --- a/net/sunrpc/netlink.c +++ b/net/sunrpc/netlink.c @@ -49,6 +49,11 @@ static const struct nla_policy sunrpc_unix_gid_set_reqs_nl_policy[SUNRPC_A_UNIX_ [SUNRPC_A_UNIX_GID_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_unix_gid_nl_policy), }; +/* SUNRPC_CMD_CACHE_FLUSH - do */ +static const struct nla_policy sunrpc_cache_flush_nl_policy[SUNRPC_A_CACHE_FLUSH_MASK + 1] = { + [SUNRPC_A_CACHE_FLUSH_MASK] = NLA_POLICY_MASK(NLA_U32, 0x3), +}; + /* Ops table for sunrpc */ static const struct genl_split_ops sunrpc_nl_ops[] = { { @@ -79,6 +84,13 @@ static const struct genl_split_ops sunrpc_nl_ops[] = { .maxattr = SUNRPC_A_UNIX_GID_REQS_REQUESTS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = SUNRPC_CMD_CACHE_FLUSH, + .doit = sunrpc_nl_cache_flush_doit, + .policy = sunrpc_cache_flush_nl_policy, + .maxattr = SUNRPC_A_CACHE_FLUSH_MASK, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group sunrpc_nl_mcgrps[] = { diff --git a/net/sunrpc/netlink.h b/net/sunrpc/netlink.h index 2aec57d27a58..2c1012303d48 100644 --- a/net/sunrpc/netlink.h +++ b/net/sunrpc/netlink.h @@ -23,6 +23,7 @@ int sunrpc_nl_unix_gid_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int sunrpc_nl_unix_gid_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); +int sunrpc_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info); enum { SUNRPC_NLGRP_NONE, diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 7703523d4246..64a2658faddb 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -818,6 +818,38 @@ int sunrpc_nl_unix_gid_set_reqs_doit(struct sk_buff *skb, return ret; } +/** + * sunrpc_nl_cache_flush_doit - flush sunrpc caches via netlink + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Flush the ip_map and/or unix_gid caches. If SUNRPC_A_CACHE_FLUSH_MASK + * is provided, only flush the caches indicated by the bitmask (bit 1 = + * ip_map, bit 2 = unix_gid). If omitted, flush both. + * + * Return 0 on success or a negative errno. + */ +int sunrpc_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct sunrpc_net *sn; + u32 mask = ~0U; + + sn = net_generic(genl_info_net(info), sunrpc_net_id); + + if (info->attrs[SUNRPC_A_CACHE_FLUSH_MASK]) + mask = nla_get_u32(info->attrs[SUNRPC_A_CACHE_FLUSH_MASK]); + + if ((mask & SUNRPC_CACHE_TYPE_IP_MAP) && + sn->ip_map_cache) + cache_purge(sn->ip_map_cache); + + if ((mask & SUNRPC_CACHE_TYPE_UNIX_GID) && + sn->unix_gid_cache) + cache_purge(sn->unix_gid_cache); + + return 0; +} + static const struct cache_detail unix_gid_cache_template = { .owner = THIS_MODULE, .hash_size = GID_HASHMAX, -- cgit v1.3-14-g43fede From 70b7e3526c53d9dd7caccdbeff5b0485640d8cf1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 25 Mar 2026 10:40:34 -0400 Subject: nfsd: add NFSD_CMD_CACHE_FLUSH netlink command Add a new NFSD_CMD_CACHE_FLUSH generic netlink command that allows userspace to flush the nfsd export caches (svc_export and expkey) without writing to /proc/net/rpc/*/flush. An optional NFSD_A_CACHE_FLUSH_MASK u32 attribute selects which caches to flush (bit 1 = svc_export, bit 2 = expkey). If the attribute is omitted, all nfsd caches are flushed. This is used by exportfs to replace its /proc-based cache_flush() with a netlink equivalent, with /proc fallback for older kernels. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 17 +++++++++++++++++ fs/nfsd/netlink.c | 12 ++++++++++++ fs/nfsd/netlink.h | 1 + fs/nfsd/nfsctl.c | 36 +++++++++++++++++++++++++++++++++++ include/uapi/linux/nfsd_netlink.h | 8 ++++++++ 5 files changed, 74 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 7030b40273fd..40eca7c15680 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -293,6 +293,14 @@ attribute-sets: type: nest nested-attributes: expkey multi-attr: true + - + name: cache-flush + attributes: + - + name: mask + type: u32 + enum: cache-type + enum-as-flags: true operations: list: @@ -438,6 +446,15 @@ operations: request: attributes: - requests + - + name: cache-flush + doc: Flush nfsd caches (svc_export and/or expkey) + attribute-set: cache-flush + flags: [admin-perm] + do: + request: + attributes: + - mask mcast-groups: list: diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index 394230e250a5..30c4f8be3df9 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -108,6 +108,11 @@ static const struct nla_policy nfsd_expkey_set_reqs_nl_policy[NFSD_A_EXPKEY_REQS [NFSD_A_EXPKEY_REQS_REQUESTS] = NLA_POLICY_NESTED(nfsd_expkey_nl_policy), }; +/* NFSD_CMD_CACHE_FLUSH - do */ +static const struct nla_policy nfsd_cache_flush_nl_policy[NFSD_A_CACHE_FLUSH_MASK + 1] = { + [NFSD_A_CACHE_FLUSH_MASK] = NLA_POLICY_MASK(NLA_U32, 0x3), +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -191,6 +196,13 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .maxattr = NFSD_A_EXPKEY_REQS_REQUESTS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_CACHE_FLUSH, + .doit = nfsd_nl_cache_flush_doit, + .policy = nfsd_cache_flush_nl_policy, + .maxattr = NFSD_A_CACHE_FLUSH_MASK, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group nfsd_nl_mcgrps[] = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index f5b338777285..cc89732ed71b 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -38,6 +38,7 @@ int nfsd_nl_svc_export_set_reqs_doit(struct sk_buff *skb, int nfsd_nl_expkey_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int nfsd_nl_expkey_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info); enum { NFSD_NLGRP_NONE, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index c93cf82e3647..bfb937e8ad7c 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -2212,6 +2213,41 @@ err_free_msg: return err; } +/** + * nfsd_nl_cache_flush_doit - flush nfsd caches via netlink + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Flush the svc_export and/or expkey caches. If NFSD_A_CACHE_FLUSH_MASK + * is provided, only flush the caches indicated by the bitmask (bit 0 = + * svc_export, bit 1 = expkey). If omitted, flush both. + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + u32 mask = ~0U; + + if (info->attrs[NFSD_A_CACHE_FLUSH_MASK]) + mask = nla_get_u32(info->attrs[NFSD_A_CACHE_FLUSH_MASK]); + + mutex_lock(&nfsd_mutex); + + if ((mask & NFSD_CACHE_TYPE_SVC_EXPORT) && + nn->svc_export_cache) + cache_purge(nn->svc_export_cache); + + if ((mask & NFSD_CACHE_TYPE_EXPKEY) && + nn->svc_expkey_cache) + cache_purge(nn->svc_expkey_cache); + + mutex_unlock(&nfsd_mutex); + + return 0; +} + int nfsd_cache_notify(struct cache_detail *cd, struct cache_head *h, u32 cache_type) { struct genlmsghdr *hdr; diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index fed7533c1533..060c43675599 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -197,6 +197,13 @@ enum { NFSD_A_EXPKEY_REQS_MAX = (__NFSD_A_EXPKEY_REQS_MAX - 1) }; +enum { + NFSD_A_CACHE_FLUSH_MASK = 1, + + __NFSD_A_CACHE_FLUSH_MAX, + NFSD_A_CACHE_FLUSH_MAX = (__NFSD_A_CACHE_FLUSH_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, @@ -212,6 +219,7 @@ enum { NFSD_CMD_SVC_EXPORT_SET_REQS, NFSD_CMD_EXPKEY_GET_REQS, NFSD_CMD_EXPKEY_SET_REQS, + NFSD_CMD_CACHE_FLUSH, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.3-14-g43fede From 37340ac2c7be914ff76fdc6bb505b204a4140268 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Thu, 21 May 2026 18:50:39 -0700 Subject: Input: userio - update maintainer name She's been committing under the name Lyude Paul for a while Signed-off-by: Vicki Pfau Link: https://patch.msgid.link/20260522015040.3953472-1-vi@endrift.com Signed-off-by: Dmitry Torokhov --- Documentation/input/userio.rst | 2 +- MAINTAINERS | 2 +- drivers/input/serio/userio.c | 4 ++-- include/uapi/linux/userio.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/input/userio.rst b/Documentation/input/userio.rst index f780c77931fe..415962152815 100644 --- a/Documentation/input/userio.rst +++ b/Documentation/input/userio.rst @@ -5,7 +5,7 @@ The userio Protocol =================== -:Copyright: |copy| 2015 Stephen Chandler Paul +:Copyright: |copy| 2015 Lyude Paul Sponsored by Red Hat diff --git a/MAINTAINERS b/MAINTAINERS index 9ec290e38b44..ba67a2668231 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -28403,7 +28403,7 @@ F: sound/drivers/pcmtest.c F: tools/testing/selftests/alsa/test-pcmtest-driver.c VIRTUAL SERIO DEVICE DRIVER -M: Stephen Chandler Paul +M: Lyude Paul S: Maintained F: drivers/input/serio/userio.c F: include/uapi/linux/userio.h diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c index 91cb7a177b2d..abca8cb6aca5 100644 --- a/drivers/input/serio/userio.c +++ b/drivers/input/serio/userio.c @@ -1,7 +1,7 @@ /* * userio kernel serio device emulation module * Copyright (C) 2015 Red Hat - * Copyright (C) 2015 Stephen Chandler Paul + * Copyright (C) 2015 Lyude Paul * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU Lesser General Public License as published by @@ -278,6 +278,6 @@ module_driver(userio_misc, misc_register, misc_deregister); MODULE_ALIAS_MISCDEV(USERIO_MINOR); MODULE_ALIAS("devname:" USERIO_NAME); -MODULE_AUTHOR("Stephen Chandler Paul "); +MODULE_AUTHOR("Lyude Paul "); MODULE_DESCRIPTION("Virtual Serio Device Support"); MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/userio.h b/include/uapi/linux/userio.h index 74c9951d2cd0..98fe7e9089c4 100644 --- a/include/uapi/linux/userio.h +++ b/include/uapi/linux/userio.h @@ -2,7 +2,7 @@ /* * userio: virtual serio device support * Copyright (C) 2015 Red Hat - * Copyright (C) 2015 Lyude (Stephen Chandler Paul) + * Copyright (C) 2015 Lyude Paul * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU Lesser General Public License as published by the -- cgit v1.3-14-g43fede From c6f1363abbff69e5bd1cd1fcf060e1510e8d6d31 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Thu, 21 May 2026 18:50:40 -0700 Subject: Input: userio - allow setting other id values Previously, only the type value was settable. The proto value is used internally for choosing the right drivers, so we should expose it. The other values make sense to expose as well. Signed-off-by: Vicki Pfau Link: https://patch.msgid.link/20260522015040.3953472-2-vi@endrift.com Signed-off-by: Dmitry Torokhov --- Documentation/input/userio.rst | 23 +++++++++++++++++++++-- drivers/input/serio/userio.c | 30 ++++++++++++++++++++++++++++++ include/uapi/linux/userio.h | 5 ++++- 3 files changed, 55 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/input/userio.rst b/Documentation/input/userio.rst index 415962152815..7aaaa629bde0 100644 --- a/Documentation/input/userio.rst +++ b/Documentation/input/userio.rst @@ -66,8 +66,27 @@ USERIO_CMD_SET_PORT_TYPE ~~~~~~~~~~~~~~~~~~~~~~~~ Sets the type of port we're emulating, where ``data`` is the port type being -set. Can be any of the macros from . For example: SERIO_8042 -would set the port type to be a normal PS/2 port. +set. Can be any of the serio type macros from . For example: +SERIO_8042 would set the port type to be a normal PS/2 port. + +USERIO_CMD_SET_PORT_PROTO +~~~~~~~~~~~~~~~~~~~~~~~~~ + +Sets the protocol of port we're emulating, where ``data`` is the protocol being +set. Can be any of the serio proto macros from . For example: +SERIO_IFORCE would set the port type to be an I-Force serial joystick. + +USERIO_CMD_SET_PORT_ID +~~~~~~~~~~~~~~~~~~~~~~ + +Sets the ``id`` value on the identification of port we're emulating, where +``data`` is the value being set. + +USERIO_CMD_SET_PORT_EXTRA +~~~~~~~~~~~~~~~~~~~~~~~~~ + +Sets the ``extra`` value on the identification of port we're emulating, where +``data`` is the value being set. USERIO_CMD_SEND_INTERRUPT ~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c index abca8cb6aca5..8c19975c84bf 100644 --- a/drivers/input/serio/userio.c +++ b/drivers/input/serio/userio.c @@ -206,6 +206,36 @@ static int userio_execute_cmd(struct userio_device *userio, userio->serio->id.type = cmd->data; break; + case USERIO_CMD_SET_PORT_EXTRA: + if (userio->running) { + dev_warn(userio_misc.this_device, + "Can't change port extra on an already running userio instance\n"); + return -EBUSY; + } + + userio->serio->id.extra = cmd->data; + break; + + case USERIO_CMD_SET_PORT_ID: + if (userio->running) { + dev_warn(userio_misc.this_device, + "Can't change port id on an already running userio instance\n"); + return -EBUSY; + } + + userio->serio->id.id = cmd->data; + break; + + case USERIO_CMD_SET_PORT_PROTO: + if (userio->running) { + dev_warn(userio_misc.this_device, + "Can't change port proto on an already running userio instance\n"); + return -EBUSY; + } + + userio->serio->id.proto = cmd->data; + break; + case USERIO_CMD_SEND_INTERRUPT: if (!userio->running) { dev_warn(userio_misc.this_device, diff --git a/include/uapi/linux/userio.h b/include/uapi/linux/userio.h index 98fe7e9089c4..550c7465af1f 100644 --- a/include/uapi/linux/userio.h +++ b/include/uapi/linux/userio.h @@ -27,7 +27,10 @@ enum userio_cmd_type { USERIO_CMD_REGISTER = 0, USERIO_CMD_SET_PORT_TYPE = 1, - USERIO_CMD_SEND_INTERRUPT = 2 + USERIO_CMD_SEND_INTERRUPT = 2, + USERIO_CMD_SET_PORT_EXTRA = 3, + USERIO_CMD_SET_PORT_ID = 4, + USERIO_CMD_SET_PORT_PROTO = 5, }; /* -- cgit v1.3-14-g43fede From 2cb5251d3d64d57c172185b9b608f704b3015f26 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 2 Jun 2026 11:09:38 +0200 Subject: futex: Provide UABI defines for robust list entry modifiers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The marker for PI futexes in the robust list is a hardcoded 0x1 which lacks any sensible form of documentation. Provide proper defines for the bit and the mask and fix up the usage sites. Thereby convert the boolean pi argument into a modifier argument, which allows new modifier bits to be trivially added and conveyed. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Mathieu Desnoyers Reviewed-by: André Almeida Link: https://patch.msgid.link/20260602090535.458758556@kernel.org --- include/uapi/linux/futex.h | 4 ++++ kernel/futex/core.c | 53 ++++++++++++++++++++++------------------------ 2 files changed, 29 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 7e2744ec8933..29bf2f65406a 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -177,6 +177,10 @@ struct robust_list_head { */ #define ROBUST_LIST_LIMIT 2048 +/* Modifiers for robust_list_head::list_op_pending */ +#define FUTEX_ROBUST_MOD_PI (0x1UL) +#define FUTEX_ROBUST_MOD_MASK (FUTEX_ROBUST_MOD_PI) + /* * bitset with all bits set for the FUTEX_xxx_BITSET OPs to request a * match of any bit. diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 79456b0ac1c6..61f4f559afa1 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1008,8 +1008,9 @@ void futex_unqueue_pi(struct futex_q *q) * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, - bool pi, bool pending_op) + unsigned int mod, bool pending_op) { + bool pi = !!(mod & FUTEX_ROBUST_MOD_PI); u32 uval, nval, mval; pid_t owner; int err; @@ -1127,21 +1128,21 @@ retry: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, - unsigned int *pi) + unsigned int *mod) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; - *entry = (void __user *)(uentry & ~1UL); - *pi = uentry & 1; + *entry = (void __user *)(uentry & ~FUTEX_ROBUST_MOD_MASK); + *mod = uentry & FUTEX_ROBUST_MOD_MASK; return 0; } /* - * Walk curr->robust_list (very carefully, it's a userspace list!) + * Walk curr->futex.robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. @@ -1149,9 +1150,8 @@ static inline int fetch_robust_entry(struct robust_list __user **entry, static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->futex.robust_list; + unsigned int limit = ROBUST_LIST_LIMIT, cur_mod, next_mod, pend_mod; struct robust_list __user *entry, *next_entry, *pending; - unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int next_pi; unsigned long futex_offset; int rc; @@ -1159,7 +1159,7 @@ static void exit_robust_list(struct task_struct *curr) * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ - if (fetch_robust_entry(&entry, &head->list.next, &pi)) + if (fetch_robust_entry(&entry, &head->list.next, &cur_mod)) return; /* * Fetch the relative futex offset: @@ -1170,7 +1170,7 @@ static void exit_robust_list(struct task_struct *curr) * Fetch any possibly pending lock-add first, and handle it * if it exists: */ - if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) + if (fetch_robust_entry(&pending, &head->list_op_pending, &pend_mod)) return; next_entry = NULL; /* avoid warning with gcc */ @@ -1179,20 +1179,20 @@ static void exit_robust_list(struct task_struct *curr) * Fetch the next entry in the list before calling * handle_futex_death: */ - rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); + rc = fetch_robust_entry(&next_entry, &entry->next, &next_mod); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, - curr, pi, HANDLE_DEATH_LIST)) + curr, cur_mod, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; - pi = next_pi; + cur_mod = next_mod; /* * Avoid excessively long or circular lists: */ @@ -1204,7 +1204,7 @@ static void exit_robust_list(struct task_struct *curr) if (pending) { handle_futex_death((void __user *)pending + futex_offset, - curr, pip, HANDLE_DEATH_PENDING); + curr, pend_mod, HANDLE_DEATH_PENDING); } } @@ -1223,29 +1223,28 @@ static void __user *futex_uaddr(struct robust_list __user *entry, */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, - compat_uptr_t __user *head, unsigned int *pi) + compat_uptr_t __user *head, unsigned int *pflags) { if (get_user(*uentry, head)) return -EFAULT; - *entry = compat_ptr((*uentry) & ~1); - *pi = (unsigned int)(*uentry) & 1; + *entry = compat_ptr((*uentry) & ~FUTEX_ROBUST_MOD_MASK); + *pflags = (unsigned int)(*uentry) & FUTEX_ROBUST_MOD_MASK; return 0; } /* - * Walk curr->robust_list (very carefully, it's a userspace list!) + * Walk curr->futex.robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { - struct compat_robust_list_head __user *head = curr->futex.compat_robust_list; + struct compat_robust_list_head __user *head = current->futex.compat_robust_list; + unsigned int limit = ROBUST_LIST_LIMIT, cur_mod, next_mod, pend_mod; struct robust_list __user *entry, *next_entry, *pending; - unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; @@ -1254,7 +1253,7 @@ static void compat_exit_robust_list(struct task_struct *curr) * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ - if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) + if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &cur_mod)) return; /* * Fetch the relative futex offset: @@ -1265,8 +1264,7 @@ static void compat_exit_robust_list(struct task_struct *curr) * Fetch any possibly pending lock-add first, and handle it * if it exists: */ - if (compat_fetch_robust_entry(&upending, &pending, - &head->list_op_pending, &pip)) + if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pend_mod)) return; next_entry = NULL; /* avoid warning with gcc */ @@ -1276,7 +1274,7 @@ static void compat_exit_robust_list(struct task_struct *curr) * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, - (compat_uptr_t __user *)&entry->next, &next_pi); + (compat_uptr_t __user *)&entry->next, &next_mod); /* * A pending lock might already be on the list, so * dont process it twice: @@ -1284,15 +1282,14 @@ static void compat_exit_robust_list(struct task_struct *curr) if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); - if (handle_futex_death(uaddr, curr, pi, - HANDLE_DEATH_LIST)) + if (handle_futex_death(uaddr, curr, cur_mod, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; - pi = next_pi; + cur_mod = next_mod; /* * Avoid excessively long or circular lists: */ @@ -1304,7 +1301,7 @@ static void compat_exit_robust_list(struct task_struct *curr) if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); - handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); + handle_futex_death(uaddr, curr, pend_mod, HANDLE_DEATH_PENDING); } } #endif -- cgit v1.3-14-g43fede From 1fd053d26f0333485cdbaa9d6e7b8cb53f54de95 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 2 Jun 2026 11:09:51 +0200 Subject: futex: Cleanup UAPI defines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make the operand defines tabular for readability sake. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: André Almeida Link: https://patch.msgid.link/20260602090535.615600933@kernel.org --- include/uapi/linux/futex.h | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 29bf2f65406a..75df1eaff75d 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -25,23 +25,22 @@ #define FUTEX_PRIVATE_FLAG 128 #define FUTEX_CLOCK_REALTIME 256 -#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME) - -#define FUTEX_WAIT_PRIVATE (FUTEX_WAIT | FUTEX_PRIVATE_FLAG) -#define FUTEX_WAKE_PRIVATE (FUTEX_WAKE | FUTEX_PRIVATE_FLAG) -#define FUTEX_REQUEUE_PRIVATE (FUTEX_REQUEUE | FUTEX_PRIVATE_FLAG) -#define FUTEX_CMP_REQUEUE_PRIVATE (FUTEX_CMP_REQUEUE | FUTEX_PRIVATE_FLAG) -#define FUTEX_WAKE_OP_PRIVATE (FUTEX_WAKE_OP | FUTEX_PRIVATE_FLAG) -#define FUTEX_LOCK_PI_PRIVATE (FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG) -#define FUTEX_LOCK_PI2_PRIVATE (FUTEX_LOCK_PI2 | FUTEX_PRIVATE_FLAG) -#define FUTEX_UNLOCK_PI_PRIVATE (FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG) -#define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG) + +#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME) + +#define FUTEX_WAIT_PRIVATE (FUTEX_WAIT | FUTEX_PRIVATE_FLAG) +#define FUTEX_WAKE_PRIVATE (FUTEX_WAKE | FUTEX_PRIVATE_FLAG) +#define FUTEX_REQUEUE_PRIVATE (FUTEX_REQUEUE | FUTEX_PRIVATE_FLAG) +#define FUTEX_CMP_REQUEUE_PRIVATE (FUTEX_CMP_REQUEUE | FUTEX_PRIVATE_FLAG) +#define FUTEX_WAKE_OP_PRIVATE (FUTEX_WAKE_OP | FUTEX_PRIVATE_FLAG) +#define FUTEX_LOCK_PI_PRIVATE (FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG) +#define FUTEX_LOCK_PI2_PRIVATE (FUTEX_LOCK_PI2 | FUTEX_PRIVATE_FLAG) +#define FUTEX_UNLOCK_PI_PRIVATE (FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG) +#define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG) #define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITSET | FUTEX_PRIVATE_FLAG) #define FUTEX_WAKE_BITSET_PRIVATE (FUTEX_WAKE_BITSET | FUTEX_PRIVATE_FLAG) -#define FUTEX_WAIT_REQUEUE_PI_PRIVATE (FUTEX_WAIT_REQUEUE_PI | \ - FUTEX_PRIVATE_FLAG) -#define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | \ - FUTEX_PRIVATE_FLAG) +#define FUTEX_WAIT_REQUEUE_PI_PRIVATE (FUTEX_WAIT_REQUEUE_PI | FUTEX_PRIVATE_FLAG) +#define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | FUTEX_PRIVATE_FLAG) /* * Flags for futex2 syscalls. -- cgit v1.3-14-g43fede From 3ca9595d9fb6cce6633a5b03d98c2aecb5499838 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 2 Jun 2026 11:09:55 +0200 Subject: futex: Add support for unlocking robust futexes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Unlocking robust non-PI futexes happens in user space with the following sequence: 1) robust_list_set_op_pending(mutex); 2) robust_list_remove(mutex); lval = 0; 3) lval = atomic_xchg(lock, lval); 4) if (lval & WAITERS) 5) sys_futex(WAKE,....); 6) robust_list_clear_op_pending(); That opens a window between #3 and #6 where the mutex could be acquired by some other task which observes that it is the last user and: A) unmaps the mutex memory B) maps a different file, which ends up covering the same address When the original task exits before reaching #6 then the kernel robust list handling observes the pending op entry and tries to fix up user space. In case that the newly mapped data contains the TID of the exiting thread at the address of the mutex/futex the kernel will set the owner died bit in that memory and therefore corrupting unrelated data. PI futexes have a similar problem both for the non-contented user space unlock and the in kernel unlock: 1) robust_list_set_op_pending(mutex); 2) robust_list_remove(mutex); lval = gettid(); 3) if (!atomic_try_cmpxchg(lock, lval, 0)) 4) sys_futex(UNLOCK_PI,....); 5) robust_list_clear_op_pending(); Address the first part of the problem where the futexes have waiters and need to enter the kernel anyway. Add a new FUTEX_ROBUST_UNLOCK flag, which is valid for the sys_futex() FUTEX_UNLOCK_PI, FUTEX_WAKE, FUTEX_WAKE_BITSET operations. This deliberately omits FUTEX_WAKE_OP from this treatment as it's unclear whether this is needed and there is no usage of it in glibc either to investigate. For the futex2 syscall family this needs to be implemented with a new syscall. The sys_futex() case [ab]uses the @uaddr2 argument to hand the pointer to robust_list_head::list_pending_op into the kernel. This argument is only evaluated when the FUTEX_ROBUST_UNLOCK bit is set and is therefore backward compatible. This is an explicit argument to avoid the lookup of the robust list pointer and retrieving the pending op pointer from there. User space has the pointer already available so it can just put it into the @uaddr2 argument. Aside of that this allows the usage of multiple robust lists in the future without any changes to the internal functions as they just operate on the provided pointer. This requires a second flag FUTEX_ROBUST_LIST32 which indicates that the robust list pointer points to an u32 and not to an u64. This is required for two reasons: 1) sys_futex() has no compat variant 2) The gaming emulators use both both 64-bit and compat 32-bit robust lists in the same 64-bit application As a consequence 32-bit applications have to set this flag unconditionally so they can run on a 64-bit kernel in compat mode unmodified. 32-bit kernels return an error code when the flag is not set. 64-bit kernels will happily clear the full 64 bits if user space fails to set it. In case of FUTEX_UNLOCK_PI this clears the robust list pending op when the unlock succeeded. In case of errors, the user space value is still locked by the caller and therefore the above cannot happen. In case of FUTEX_WAKE* this does the unlock of the futex in the kernel and clears the robust list pending op when the unlock was successful. If not, the user space value is still locked and user space has to deal with the returned error. That means that the unlocking of non-PI robust futexes has to use the same try_cmpxchg() unlock scheme as PI futexes. If the clearing of the pending list op fails (fault) then the kernel clears the registered robust list pointer if it matches to prevent that exit() will try to handle invalid data. That's a valid paranoid decision because the robust list head sits usually in the TLS and if the TLS is not longer accessible then the chance for fixing up the resulting mess is very close to zero. The problem of non-contended unlocks still exists and will be addressed separately. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: André Almeida Link: https://patch.msgid.link/20260602090535.670514505@kernel.org --- include/uapi/linux/futex.h | 29 ++++++++++++++++++++++++- io_uring/futex.c | 2 +- kernel/futex/core.c | 53 ++++++++++++++++++++++++++++++++++++++++++++-- kernel/futex/futex.h | 15 +++++++++++-- kernel/futex/pi.c | 15 +++++++++++-- kernel/futex/syscalls.c | 13 +++++++++--- kernel/futex/waitwake.c | 30 ++++++++++++++++++++++++-- 7 files changed, 144 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 75df1eaff75d..10a36c551675 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -25,8 +25,11 @@ #define FUTEX_PRIVATE_FLAG 128 #define FUTEX_CLOCK_REALTIME 256 +#define FUTEX_ROBUST_UNLOCK 512 +#define FUTEX_ROBUST_LIST32 1024 -#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME) +#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME | \ + FUTEX_ROBUST_UNLOCK | FUTEX_ROBUST_LIST32) #define FUTEX_WAIT_PRIVATE (FUTEX_WAIT | FUTEX_PRIVATE_FLAG) #define FUTEX_WAKE_PRIVATE (FUTEX_WAKE | FUTEX_PRIVATE_FLAG) @@ -42,6 +45,30 @@ #define FUTEX_WAIT_REQUEUE_PI_PRIVATE (FUTEX_WAIT_REQUEUE_PI | FUTEX_PRIVATE_FLAG) #define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | FUTEX_PRIVATE_FLAG) +/* + * Operations to unlock a futex, clear the robust list pending op pointer and + * wake waiters. + */ +#define FUTEX_UNLOCK_PI_LIST64 (FUTEX_UNLOCK_PI | FUTEX_ROBUST_UNLOCK) +#define FUTEX_UNLOCK_PI_LIST64_PRIVATE (FUTEX_UNLOCK_PI_LIST64 | FUTEX_PRIVATE_FLAG) +#define FUTEX_UNLOCK_PI_LIST32 (FUTEX_UNLOCK_PI | FUTEX_ROBUST_UNLOCK | \ + FUTEX_ROBUST_LIST32) +#define FUTEX_UNLOCK_PI_LIST32_PRIVATE (FUTEX_UNLOCK_PI_LIST32 | FUTEX_PRIVATE_FLAG) + +#define FUTEX_UNLOCK_WAKE_LIST64 (FUTEX_WAKE | FUTEX_ROBUST_UNLOCK) +#define FUTEX_UNLOCK_WAKE_LIST64_PRIVATE (FUTEX_UNLOCK_WAKE_LIST64 | FUTEX_PRIVATE_FLAG) + +#define FUTEX_UNLOCK_WAKE_LIST32 (FUTEX_WAKE | FUTEX_ROBUST_UNLOCK | \ + FUTEX_ROBUST_LIST32) +#define FUTEX_UNLOCK_WAKE_LIST32_PRIVATE (FUTEX_UNLOCK_WAKE_LIST32 | FUTEX_PRIVATE_FLAG) + +#define FUTEX_UNLOCK_BITSET_LIST64 (FUTEX_WAKE_BITSET | FUTEX_ROBUST_UNLOCK) +#define FUTEX_UNLOCK_BITSET_LIST64_PRIVATE (FUTEX_UNLOCK_BITSET_LIST64 | FUTEX_PRIVATE_FLAG) + +#define FUTEX_UNLOCK_BITSET_LIST32 (FUTEX_WAKE_BITSET | FUTEX_ROBUST_UNLOCK | \ + FUTEX_ROBUST_LIST32) +#define FUTEX_UNLOCK_BITSET_LIST32_PRIVATE (FUTEX_UNLOCK_BITSET_LIST32 | FUTEX_PRIVATE_FLAG) + /* * Flags for futex2 syscalls. * diff --git a/io_uring/futex.c b/io_uring/futex.c index 9cc1788ef4c6..906701b3c5c6 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -327,7 +327,7 @@ int io_futex_wake(struct io_kiocb *req, unsigned int issue_flags) * Strict flags - ensure that waking 0 futexes yields a 0 result. * See commit 43adf8449510 ("futex: FLAGS_STRICT") for details. */ - ret = futex_wake(iof->uaddr, FLAGS_STRICT | iof->futex_flags, + ret = futex_wake(iof->uaddr, FLAGS_STRICT | iof->futex_flags, NULL, iof->futex_val, iof->futex_mask); if (ret < 0) req_set_fail(req); diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 61f4f559afa1..77ccb7787c34 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1062,7 +1062,7 @@ retry: owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { - futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1, FUTEX_BITSET_MATCH_ANY); return 0; } @@ -1116,7 +1116,7 @@ retry: * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { - futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1, FUTEX_BITSET_MATCH_ANY); } @@ -1208,6 +1208,27 @@ static void exit_robust_list(struct task_struct *curr) } } +static bool robust_list_clear_pending(unsigned long __user *pop) +{ + struct robust_list_head __user *head = current->futex.robust_list; + + if (!put_user(0UL, pop)) + return true; + + /* + * Just give up. The robust list head is usually part of TLS, so the + * chance that this gets resolved is close to zero. + * + * If @pop_addr is the robust_list_head::list_op_pending pointer then + * clear the robust list head pointer to prevent further damage when the + * task exits. Better a few stale futexes than corrupted memory. But + * that's mostly an academic exercise. + */ + if (pop == (unsigned long __user *)&head->list_op_pending) + current->futex.robust_list = NULL; + return false; +} + #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) @@ -1304,6 +1325,21 @@ static void compat_exit_robust_list(struct task_struct *curr) handle_futex_death(uaddr, curr, pend_mod, HANDLE_DEATH_PENDING); } } + +static bool compat_robust_list_clear_pending(u32 __user *pop) +{ + struct compat_robust_list_head __user *head = current->futex.compat_robust_list; + + if (!put_user(0U, pop)) + return true; + + /* See comment in robust_list_clear_pending(). */ + if (pop == &head->list_op_pending) + current->futex.compat_robust_list = NULL; + return false; +} +#else +static bool compat_robust_list_clear_pending(u32 __user *pop_addr) { return false; } #endif #ifdef CONFIG_FUTEX_PI @@ -1397,6 +1433,19 @@ static void exit_pi_state_list(struct task_struct *curr) static inline void exit_pi_state_list(struct task_struct *curr) { } #endif +bool futex_robust_list_clear_pending(void __user *pop, unsigned int flags) +{ + bool size32bit = !!(flags & FLAGS_ROBUST_LIST32); + + if (!IS_ENABLED(CONFIG_64BIT) && !size32bit) + return false; + + if (IS_ENABLED(CONFIG_64BIT) && size32bit) + return compat_robust_list_clear_pending(pop); + + return robust_list_clear_pending(pop); +} + static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->futex.robust_list)) { diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 9f6bf6f585fc..79ef2c709c81 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -40,6 +40,8 @@ #define FLAGS_NUMA 0x0080 #define FLAGS_STRICT 0x0100 #define FLAGS_MPOL 0x0200 +#define FLAGS_ROBUST_UNLOCK 0x0400 +#define FLAGS_ROBUST_LIST32 0x0800 /* FUTEX_ to FLAGS_ */ static inline unsigned int futex_to_flags(unsigned int op) @@ -52,6 +54,12 @@ static inline unsigned int futex_to_flags(unsigned int op) if (op & FUTEX_CLOCK_REALTIME) flags |= FLAGS_CLOCKRT; + if (op & FUTEX_ROBUST_UNLOCK) + flags |= FLAGS_ROBUST_UNLOCK; + + if (op & FUTEX_ROBUST_LIST32) + flags |= FLAGS_ROBUST_LIST32; + return flags; } @@ -449,13 +457,16 @@ extern int futex_unqueue_multiple(struct futex_vector *v, int count); extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to); -extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); +extern int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop, + int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op); -extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags); +extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags, void __user *pop); extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock); +bool futex_robust_list_clear_pending(void __user *pop, unsigned int flags); + #endif /* _FUTEX_H */ diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index e037a97fe277..9dd5c0b1ac6a 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -1139,7 +1139,7 @@ out: * This is the in-kernel slowpath: we look up the PI state (if any), * and do the rt-mutex unlock. */ -int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) +static int __futex_unlock_pi(u32 __user *uaddr, unsigned int flags) { u32 curval, uval, vpid = task_pid_vnr(current); union futex_key key = FUTEX_KEY_INIT; @@ -1148,7 +1148,6 @@ int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) if (!IS_ENABLED(CONFIG_FUTEX_PI)) return -ENOSYS; - retry: if (get_user(uval, uaddr)) return -EFAULT; @@ -1302,3 +1301,15 @@ pi_faulted: return ret; } +int futex_unlock_pi(u32 __user *uaddr, unsigned int flags, void __user *pop) +{ + int ret = __futex_unlock_pi(uaddr, flags); + + if (ret || !(flags & FLAGS_ROBUST_UNLOCK)) + return ret; + + if (!futex_robust_list_clear_pending(pop, flags)) + return -EFAULT; + + return 0; +} diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 8944ff4930d7..2fa19d9d008d 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -118,6 +118,13 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, return -ENOSYS; } + if (flags & FLAGS_ROBUST_UNLOCK) { + if (cmd != FUTEX_WAKE && + cmd != FUTEX_WAKE_BITSET && + cmd != FUTEX_UNLOCK_PI) + return -ENOSYS; + } + switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; @@ -128,7 +135,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAKE_BITSET: - return futex_wake(uaddr, flags, val, val3); + return futex_wake(uaddr, flags, uaddr2, val, val3); case FUTEX_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: @@ -141,7 +148,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: - return futex_unlock_pi(uaddr, flags); + return futex_unlock_pi(uaddr, flags, uaddr2); case FUTEX_TRYLOCK_PI: return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: @@ -375,7 +382,7 @@ SYSCALL_DEFINE4(futex_wake, if (!futex_validate_input(flags, mask)) return -EINVAL; - return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); + return futex_wake(uaddr, FLAGS_STRICT | flags, NULL, nr, mask); } /* diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index ceed9d879059..8f5e5d302356 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -149,13 +149,36 @@ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) wake_q_add_safe(wake_q, p); } +/* + * If requested, clear the robust list pending op and unlock the futex + */ +static bool futex_robust_unlock(u32 __user *uaddr, unsigned int flags, void __user *pop) +{ + if (!(flags & FLAGS_ROBUST_UNLOCK)) + return true; + + /* First unlock the futex, which requires release semantics. */ + scoped_user_write_access(uaddr, efault) + unsafe_atomic_store_release_user(0, uaddr, efault); + + /* + * Clear the pending list op now. If that fails, then the task is in + * deeper trouble as the robust list head is usually part of the TLS. + * The chance of survival is close to zero. + */ + return futex_robust_list_clear_pending(pop, flags); + +efault: + return false; +} + /* * Wake up waiters matching bitset queued on this futex (uaddr). */ -int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) +int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop, int nr_wake, u32 bitset) { - struct futex_q *this, *next; union futex_key key = FUTEX_KEY_INIT; + struct futex_q *this, *next; DEFINE_WAKE_Q(wake_q); int ret; @@ -166,6 +189,9 @@ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) if (unlikely(ret != 0)) return ret; + if (!futex_robust_unlock(uaddr, flags, pop)) + return -EFAULT; + if ((flags & FLAGS_STRICT) && !nr_wake) return 0; -- cgit v1.3-14-g43fede From afabbb56a7262979a75259e2710019aa8ced3e8a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 2 Jun 2026 19:03:45 +0000 Subject: geneve: Introduce IFLA_GENEVE_LOCAL and IFLA_GENEVE_LOCAL6. By default, a GENEVE device bind()s its underlying UDP socket(s) to the IPv4 or IPv6 wildcard address because there is no way to specify a specific local IP address to bind() to. This prevents deploying multiple GENEVE devices on a multi-homed host where each device should be isolated and bound to a different local IP address on the same UDP port. Let's introduce new options, IFLA_GENEVE_LOCAL and IFLA_GENEVE_LOCAL6, to allow specifying a local IPv4/IPv6 address for the backend UDP socket. By default, when collect metadata mode (IFLA_GENEVE_COLLECT_METADATA) is enabled, both IPv4 and IPv6 sockets are created. However, if a source address is specified via the new attributes, only a single socket corresponding to that specific address family is created. Accordingly, geneve_find_sock() and geneve_find_dev() are updated to take the source address into account, ensuring that multiple devices and sockets configured with different source addresses can coexist without conflict. In addition, the source address is validated in geneve_xmit_skb() and geneve6_xmit_skb(), so the BPF prog must set it in bpf_tunnel_key. With this change, multiple GENEVE devices can be successfully created and bound to their respective local IP addresses: (*) "local" is the keyword for IFLA_GENEVE_LOCAL / IFLA_GENEVE_LOCAL6 # for i in $(seq 1 2); do ip link add geneve4_${i} type geneve local 192.168.0.${i} external ip addr add 192.168.0.${i}/24 dev geneve4_${i} ip link set geneve4_${i} up ip link add geneve6_${i} type geneve local 2001:9292::${i} external ip addr add 2001:9292::${i}/64 dev geneve6_${i} nodad ip link set geneve6_${i} up done # ip -d l | grep geneve 9: geneve4_1: ... geneve external id 0 local 192.168.0.1 ... 10: geneve6_1: ... geneve external id 0 local 2001:9292::1 ... 11: geneve4_2: ... geneve external id 0 local 192.168.0.2 ... 12: geneve6_2: ... geneve external id 0 local 2001:9292::2 ... # ss -ua | grep geneve UNCONN 0 0 192.168.0.2:geneve 0.0.0.0:* UNCONN 0 0 192.168.0.1:geneve 0.0.0.0:* UNCONN 0 0 [2001:9292::2]:geneve *:* UNCONN 0 0 [2001:9292::1]:geneve *:* Note that even if the local address is explicitly configured with the wildcard address, kernel does not dump it except for devices with IFLA_GENEVE_COLLECT_METADATA. This is consistent with the behaviour of is_tnl_info_zero(), which treats the wildcard remote address as not configured. ## ynl example. # ./tools/net/ynl/pyynl/cli.py \ --spec ./Documentation/netlink/specs/rt-link.yaml \ --do newlink --create \ --json '{"ifname": "geneve0", "linkinfo": {"kind":"geneve", "data": {"local": "0.0.0.0", "collect-metadata": true}}}' # ./tools/net/ynl/pyynl/cli.py \ --spec ./Documentation/netlink/specs/rt-link.yaml \ --do getlink \ --json '{"ifname": "geneve0"}' --output-json | \ jq .linkinfo.data.local "0.0.0.0" Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260602190436.139591-6-kuniyu@google.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/rt-link.yaml | 9 ++ drivers/net/geneve.c | 167 +++++++++++++++++++++++++++++-- include/uapi/linux/if_link.h | 2 + 3 files changed, 169 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index a5c0297818c6..7f8e3ad3a405 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -1941,6 +1941,15 @@ attribute-sets: - name: gro-hint type: flag + - + name: local + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: local6 + type: binary + display-hint: ipv6 - name: linkinfo-hsr-attrs name-prefix: ifla-hsr- diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 3a62d132a8c4..da17b4f6fda5 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -775,9 +775,10 @@ static struct sock *geneve_create_sock(struct net *net, udp_conf.family = AF_INET6; udp_conf.ipv6_v6only = 1; udp_conf.use_udp6_rx_checksums = geneve->cfg.use_udp6_rx_checksums; + udp_conf.local_ip6 = info->key.u.ipv6.src; } else { udp_conf.family = AF_INET; - udp_conf.local_ip.s_addr = htonl(INADDR_ANY); + udp_conf.local_ip.s_addr = info->key.u.ipv4.src; } udp_conf.local_udp_port = info->key.tp_dst; @@ -1061,6 +1062,16 @@ static struct geneve_sock *geneve_find_sock(struct net *net, if (gs->gro_hint != gro_hint) continue; + if (family == AF_INET && + inet_sk(gs->sk)->inet_saddr != info->key.u.ipv4.src) + continue; + +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && + !ipv6_addr_equal(&gs->sk->sk_v6_rcv_saddr, &info->key.u.ipv6.src)) + continue; +#endif + return gs; } @@ -1327,6 +1338,12 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (IS_ERR(rt)) return PTR_ERR(rt); + if (geneve->cfg.info.key.u.ipv4.src && + saddr != geneve->cfg.info.key.u.ipv4.src) { + dst_release(&rt->dst); + return -EADDRNOTAVAIL; + } + err = skb_tunnel_check_pmtu(skb, &rt->dst, GENEVE_IPV4_HLEN + info->options_len + geneve_build_gro_hint_opt(geneve, skb), @@ -1438,6 +1455,12 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (IS_ERR(dst)) return PTR_ERR(dst); + if (!ipv6_addr_any(&geneve->cfg.info.key.u.ipv6.src) && + !ipv6_addr_equal(&saddr, &geneve->cfg.info.key.u.ipv6.src)) { + dst_release(dst); + return -EADDRNOTAVAIL; + } + err = skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len + geneve_build_gro_hint_opt(geneve, skb), @@ -1729,6 +1752,8 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_INNER_PROTO_INHERIT] = { .type = NLA_FLAG }, [IFLA_GENEVE_PORT_RANGE] = NLA_POLICY_EXACT_LEN(sizeof(struct ifla_geneve_port_range)), [IFLA_GENEVE_GRO_HINT] = { .type = NLA_FLAG }, + [IFLA_GENEVE_LOCAL] = { .type = NLA_BE32 }, + [IFLA_GENEVE_LOCAL6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], @@ -1788,7 +1813,45 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } +static bool geneve_saddr_wildcard(const struct ip_tunnel_info *info) +{ + if (ip_tunnel_info_af(info) == AF_INET) { + if (!info->key.u.ipv4.src) + return true; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (ipv6_addr_any(&info->key.u.ipv6.src)) + return true; +#endif + } + + return false; +} + +static bool geneve_saddr_conflict(const struct ip_tunnel_info *a, + const struct ip_tunnel_info *b) +{ + if (ip_tunnel_info_af(a) != ip_tunnel_info_af(b)) + return false; + + if (geneve_saddr_wildcard(a) || geneve_saddr_wildcard(b)) + return true; + + if (ip_tunnel_info_af(a) == AF_INET) { + if (a->key.u.ipv4.src == b->key.u.ipv4.src) + return true; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (ipv6_addr_equal(&a->key.u.ipv6.src, &b->key.u.ipv6.src)) + return true; +#endif + } + + return false; +} + static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, + const struct geneve_config *cfg, const struct ip_tunnel_info *info, bool *tun_on_same_port, bool *tun_collect_md) @@ -1798,8 +1861,10 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, *tun_on_same_port = false; *tun_collect_md = false; list_for_each_entry(geneve, &gn->geneve_list, next) { - if (info->key.tp_dst == geneve->cfg.info.key.tp_dst) { - *tun_collect_md = geneve->cfg.collect_md; + if (info->key.tp_dst == geneve->cfg.info.key.tp_dst && + (cfg->dualstack || geneve->cfg.dualstack || + geneve_saddr_conflict(info, &geneve->cfg.info))) { + *tun_collect_md |= geneve->cfg.collect_md; *tun_on_same_port = true; } if (info->key.tun_id == geneve->cfg.info.key.tun_id && @@ -1815,7 +1880,12 @@ static bool is_tnl_info_zero(const struct ip_tunnel_info *info) return !(info->key.tun_id || info->key.tos || !ip_tunnel_flags_empty(info->key.tun_flags) || info->key.ttl || info->key.label || info->key.tp_src || - memchr_inv(&info->key.u, 0, sizeof(info->key.u))); +#if IS_ENABLED(CONFIG_IPV6) + (ip_tunnel_info_af(info) == AF_INET6 && + !ipv6_addr_any(&info->key.u.ipv6.dst)) || +#endif + (ip_tunnel_info_af(info) == AF_INET && + info->key.u.ipv4.dst)); } static bool geneve_dst_addr_equal(struct ip_tunnel_info *a, @@ -1846,7 +1916,7 @@ static int geneve_configure(struct net *net, struct net_device *dev, geneve->net = net; geneve->dev = dev; - t = geneve_find_dev(gn, info, &tun_on_same_port, &tun_collect_md); + t = geneve_find_dev(gn, cfg, info, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; @@ -1864,13 +1934,13 @@ static int geneve_configure(struct net *net, struct net_device *dev, if (cfg->collect_md) { if (tun_on_same_port) { NL_SET_ERR_MSG(extack, - "There can be only one externally controlled device on a destination port"); + "There can be only one externally controlled device on a destination port and a source address"); return -EPERM; } } else { if (tun_collect_md) { NL_SET_ERR_MSG(extack, - "There already exists an externally controlled device on this destination port"); + "There already exists an externally controlled device on this destination port and the source address"); return -EPERM; } } @@ -1917,9 +1987,10 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], cfg->dualstack = true; } - if (data[IFLA_GENEVE_REMOTE] && data[IFLA_GENEVE_REMOTE6]) { + if ((data[IFLA_GENEVE_LOCAL] || data[IFLA_GENEVE_REMOTE]) && + (data[IFLA_GENEVE_LOCAL6] || data[IFLA_GENEVE_REMOTE6])) { NL_SET_ERR_MSG(extack, - "Cannot specify both IPv4 and IPv6 Remote addresses"); + "Cannot specify both IPv4/IPv6 Remote/Local addresses"); return -EINVAL; } @@ -1972,6 +2043,65 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], #endif } + if (data[IFLA_GENEVE_LOCAL]) { + if (changelink) { + __be32 src = nla_get_in_addr(data[IFLA_GENEVE_LOCAL]); + + if (ip_tunnel_info_af(info) == AF_INET6 || + src != info->key.u.ipv4.src) { + attrtype = IFLA_GENEVE_LOCAL; + goto change_notsup; + } + } else { + info->key.u.ipv4.src = nla_get_in_addr(data[IFLA_GENEVE_LOCAL]); + + if (ipv4_is_multicast(info->key.u.ipv4.src)) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LOCAL], + "Local IPv4 address cannot be Multicast"); + return -EINVAL; + } + + cfg->dualstack = false; + } + } + + if (data[IFLA_GENEVE_LOCAL6]) { +#if IS_ENABLED(CONFIG_IPV6) + if (changelink) { + struct in6_addr src = nla_get_in6_addr(data[IFLA_GENEVE_LOCAL6]); + + if (ip_tunnel_info_af(info) == AF_INET || + !ipv6_addr_equal(&src, &info->key.u.ipv6.src)) { + attrtype = IFLA_GENEVE_LOCAL6; + goto change_notsup; + } + } else { + int addr_type; + + info->mode = IP_TUNNEL_INFO_IPV6; + info->key.u.ipv6.src = nla_get_in6_addr(data[IFLA_GENEVE_LOCAL6]); + + addr_type = ipv6_addr_type(&info->key.u.ipv6.src); + if (addr_type & IPV6_ADDR_LINKLOCAL) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LOCAL6], + "Local IPv6 address cannot be link-local"); + return -EINVAL; + } + if (addr_type & IPV6_ADDR_MULTICAST) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LOCAL6], + "Local IPv6 address cannot be Multicast"); + return -EINVAL; + } + + cfg->dualstack = false; + } +#else + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LOCAL6], + "IPv6 support not enabled in the kernel"); + return -EPFNOSUPPORT; +#endif + } + if (data[IFLA_GENEVE_ID]) { __u32 vni; __u8 tvni[3]; @@ -2265,6 +2395,7 @@ static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_DF */ @@ -2320,6 +2451,24 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) #endif } + if (!geneve->cfg.dualstack) { + if (ip_tunnel_info_af(info) == AF_INET) { + if ((info->key.u.ipv4.src || + geneve->cfg.collect_md) && + nla_put_in_addr(skb, IFLA_GENEVE_LOCAL, + info->key.u.ipv4.src)) + goto nla_put_failure; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if ((!ipv6_addr_any(&info->key.u.ipv6.src) || + geneve->cfg.collect_md) && + nla_put_in6_addr(skb, IFLA_GENEVE_LOCAL6, + &info->key.u.ipv6.src)) + goto nla_put_failure; +#endif + } + } + if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) || nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) || nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label)) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 46413392b402..363526549a01 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1506,6 +1506,8 @@ enum { IFLA_GENEVE_INNER_PROTO_INHERIT, IFLA_GENEVE_PORT_RANGE, IFLA_GENEVE_GRO_HINT, + IFLA_GENEVE_LOCAL, + IFLA_GENEVE_LOCAL6, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) -- cgit v1.3-14-g43fede From a9d155ea9b44d9b979796506bec518222f10b9e6 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Tue, 26 May 2026 21:09:51 +0200 Subject: xfrm: add XFRM_MSG_MIGRATE_STATE for single SA migration Add a new netlink method to migrate a single xfrm_state. Unlike the existing migration mechanism (SA + policy), this supports migrating only the SA and allows changing the reqid. The SA is looked up via xfrm_usersa_id, which uniquely identifies it, so old_saddr is not needed. old_daddr is carried in xfrm_usersa_id.daddr. The reqid is invariant in the old migration. Signed-off-by: Antony Antony Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 10 +- include/uapi/linux/xfrm.h | 25 ++++ net/xfrm/xfrm_compat.c | 5 +- net/xfrm/xfrm_policy.c | 17 +++ net/xfrm/xfrm_state.c | 29 +++- net/xfrm/xfrm_user.c | 333 +++++++++++++++++++++++++++++++++++++++++++- security/selinux/nlmsgtab.c | 3 +- 7 files changed, 405 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 5515c7b10020..e2cb2d0e5cee 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -684,12 +684,20 @@ struct xfrm_migrate { xfrm_address_t new_saddr; struct xfrm_encap_tmpl *encap; struct xfrm_user_offload *xuo; + struct xfrm_mark old_mark; + const struct xfrm_mark *new_mark; + struct xfrm_mark smark; u8 proto; u8 mode; - u16 reserved; + u16 msg_type; /* XFRM_MSG_MIGRATE or XFRM_MSG_MIGRATE_STATE */ + u32 flags; u32 old_reqid; + u32 new_reqid; + u32 nat_keepalive_interval; + u32 mapping_maxage; u16 old_family; u16 new_family; + const struct xfrm_selector *new_sel; }; #define XFRM_KM_TIMEOUT 30 diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index a23495c0e0a1..051f8066efd1 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -227,6 +227,9 @@ enum { #define XFRM_MSG_SETDEFAULT XFRM_MSG_SETDEFAULT XFRM_MSG_GETDEFAULT, #define XFRM_MSG_GETDEFAULT XFRM_MSG_GETDEFAULT + + XFRM_MSG_MIGRATE_STATE, +#define XFRM_MSG_MIGRATE_STATE XFRM_MSG_MIGRATE_STATE __XFRM_MSG_MAX }; #define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1) @@ -507,6 +510,28 @@ struct xfrm_user_migrate { __u16 new_family; }; +struct xfrm_user_migrate_state { + struct xfrm_usersa_id id; + xfrm_address_t new_daddr; + xfrm_address_t new_saddr; + struct xfrm_mark old_mark; + struct xfrm_selector new_sel; + __u32 new_reqid; + __u32 flags; + __u16 new_family; + __u16 reserved; +}; + +/* Flags for xfrm_user_migrate_state.flags */ +enum xfrm_migrate_state_flags { + XFRM_MIGRATE_STATE_CLEAR_OFFLOAD = 1, /* do not inherit offload from existing SA */ + XFRM_MIGRATE_STATE_UPDATE_H2H_SEL = 2, /* update H2H selector from new daddr/saddr */ +}; + +/* All flags defined as of this header version; unknown bits are rejected. */ +#define XFRM_MIGRATE_STATE_KNOWN_FLAGS \ + (XFRM_MIGRATE_STATE_CLEAR_OFFLOAD | XFRM_MIGRATE_STATE_UPDATE_H2H_SEL) + struct xfrm_user_mapping { struct xfrm_usersa_id id; __u32 reqid; diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index b8d2e6930041..670e3512fc09 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -94,7 +94,8 @@ static const int compat_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), - [XFRM_MSG_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping) + [XFRM_MSG_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping), + [XFRM_MSG_MIGRATE_STATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_migrate_state), }; static const struct nla_policy compat_policy[XFRMA_MAX+1] = { @@ -162,6 +163,7 @@ static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, case XFRM_MSG_NEWAE: case XFRM_MSG_REPORT: case XFRM_MSG_MIGRATE: + case XFRM_MSG_MIGRATE_STATE: case XFRM_MSG_NEWSADINFO: case XFRM_MSG_NEWSPDINFO: case XFRM_MSG_MAPPING: @@ -498,6 +500,7 @@ static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, case XFRM_MSG_GETAE: case XFRM_MSG_REPORT: case XFRM_MSG_MIGRATE: + case XFRM_MSG_MIGRATE_STATE: case XFRM_MSG_NEWSADINFO: case XFRM_MSG_GETSADINFO: case XFRM_MSG_NEWSPDINFO: diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index cf05d778e2dd..1c558362d375 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4643,6 +4643,21 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate, return 0; } +/* + * Fill migrate fields that are invariant in XFRM_MSG_MIGRATE: inherited + * from the existing SA unchanged. XFRM_MSG_MIGRATE_STATE can update these. + */ +static void xfrm_migrate_copy_old(const struct xfrm_state *x, + struct xfrm_migrate *mp) +{ + mp->msg_type = XFRM_MSG_MIGRATE; + mp->smark = x->props.smark; + mp->new_reqid = x->props.reqid; + mp->nat_keepalive_interval = x->nat_keepalive_interval; + mp->mapping_maxage = x->mapping_maxage; + mp->new_mark = &x->mark; +} + int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k, struct net *net, @@ -4682,6 +4697,8 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, nx_cur++; mp->encap = encap; mp->xuo = xuo; + xfrm_migrate_copy_old(x, mp); + xc = xfrm_state_migrate(x, mp, net, extack); if (xc) { x_new[nx_new] = xc; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 043e573c4f32..2c738e980b3f 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1974,11 +1974,25 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, goto out; memcpy(&x->id, &orig->id, sizeof(x->id)); - memcpy(&x->sel, &orig->sel, sizeof(x->sel)); + if (m->msg_type == XFRM_MSG_MIGRATE_STATE) { + if (m->flags & XFRM_MIGRATE_STATE_UPDATE_H2H_SEL) { + u8 prefixlen = (m->new_family == AF_INET6) ? 128 : 32; + + x->sel = orig->sel; + x->sel.family = m->new_family; + x->sel.prefixlen_d = prefixlen; + x->sel.prefixlen_s = prefixlen; + x->sel.daddr = m->new_daddr; + x->sel.saddr = m->new_saddr; + } else { + x->sel = *m->new_sel; + } + } else { + x->sel = orig->sel; + } memcpy(&x->lft, &orig->lft, sizeof(x->lft)); x->props.mode = orig->props.mode; x->props.replay_window = orig->props.replay_window; - x->props.reqid = orig->props.reqid; if (orig->aalg) { x->aalg = xfrm_algo_auth_clone(orig->aalg); @@ -2011,8 +2025,8 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, x->encap = kmemdup(m->encap, sizeof(*x->encap), GFP_KERNEL); if (!x->encap) goto error; - x->mapping_maxage = orig->mapping_maxage; - x->nat_keepalive_interval = orig->nat_keepalive_interval; + x->mapping_maxage = m->mapping_maxage; + x->nat_keepalive_interval = m->nat_keepalive_interval; } if (orig->security) @@ -2029,8 +2043,9 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, if (xfrm_replay_clone(x, orig)) goto error; - memcpy(&x->mark, &orig->mark, sizeof(x->mark)); - memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); + x->mark = m->new_mark ? *m->new_mark : m->old_mark; + + x->props.smark = m->smark; x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; @@ -2053,7 +2068,7 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, goto error; } - + x->props.reqid = m->new_reqid; x->props.family = m->new_family; memcpy(&x->id.daddr, &m->new_daddr, sizeof(x->id.daddr)); memcpy(&x->props.saddr, &m->new_saddr, sizeof(x->props.saddr)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index de857ef65b2f..b9fbb8d13c1a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1201,6 +1201,16 @@ static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb) return 0; } +static void xso_to_xuo(const struct xfrm_dev_offload *xso, + struct xfrm_user_offload *xuo) +{ + xuo->ifindex = xso->dev->ifindex; + if (xso->dir == XFRM_DEV_OFFLOAD_IN) + xuo->flags = XFRM_OFFLOAD_INBOUND; + if (xso->type == XFRM_DEV_OFFLOAD_PACKET) + xuo->flags |= XFRM_OFFLOAD_PACKET; +} + static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb) { struct xfrm_user_offload *xuo; @@ -1212,11 +1222,7 @@ static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb) xuo = nla_data(attr); memset(xuo, 0, sizeof(*xuo)); - xuo->ifindex = xso->dev->ifindex; - if (xso->dir == XFRM_DEV_OFFLOAD_IN) - xuo->flags = XFRM_OFFLOAD_INBOUND; - if (xso->type == XFRM_DEV_OFFLOAD_PACKET) - xuo->flags |= XFRM_OFFLOAD_PACKET; + xso_to_xuo(xso, xuo); return 0; } @@ -1341,7 +1347,7 @@ static int copy_to_user_encap(struct xfrm_encap_tmpl *ep, struct sk_buff *skb) return 0; } -static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m) +static int xfrm_smark_put(struct sk_buff *skb, const struct xfrm_mark *m) { int ret = 0; @@ -3090,6 +3096,25 @@ nomem: } #ifdef CONFIG_XFRM_MIGRATE +static void copy_from_user_migrate_state(struct xfrm_migrate *ma, + const struct xfrm_user_migrate_state *um) +{ + memcpy(&ma->old_daddr, &um->id.daddr, sizeof(ma->old_daddr)); + memcpy(&ma->new_daddr, &um->new_daddr, sizeof(ma->new_daddr)); + memcpy(&ma->new_saddr, &um->new_saddr, sizeof(ma->new_saddr)); + + ma->proto = um->id.proto; + ma->new_reqid = um->new_reqid; + + ma->old_family = um->id.family; + ma->new_family = um->new_family; + + ma->old_mark = um->old_mark; + ma->flags = um->flags; + ma->new_sel = &um->new_sel; + ma->msg_type = XFRM_MSG_MIGRATE_STATE; +} + static int copy_from_user_migrate(struct xfrm_migrate *ma, struct xfrm_kmaddress *k, struct nlattr **attrs, int *num, @@ -3129,6 +3154,7 @@ static int copy_from_user_migrate(struct xfrm_migrate *ma, ma->old_family = um->old_family; ma->new_family = um->new_family; + ma->msg_type = XFRM_MSG_MIGRATE; } *num = i; @@ -3139,7 +3165,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct xfrm_userpolicy_id *pi = nlmsg_data(nlh); - struct xfrm_migrate m[XFRM_MAX_DEPTH]; + struct xfrm_migrate m[XFRM_MAX_DEPTH] = {}; struct xfrm_kmaddress km, *kmp; u8 type; int err; @@ -3192,7 +3218,298 @@ error: kfree(xuo); return err; } + +static int build_migrate_state(struct sk_buff *skb, + const struct xfrm_user_migrate_state *um, + const struct xfrm_migrate *m, + u8 dir, u32 portid, u32 seq) +{ + int err; + struct nlmsghdr *nlh; + struct xfrm_user_migrate_state *hdr; + + nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_MIGRATE_STATE, + sizeof(struct xfrm_user_migrate_state), 0); + if (!nlh) + return -EMSGSIZE; + + hdr = nlmsg_data(nlh); + *hdr = *um; + hdr->new_sel = *m->new_sel; + + if (m->encap) { + err = nla_put(skb, XFRMA_ENCAP, sizeof(*m->encap), m->encap); + if (err) + goto out_cancel; + } + + if (m->xuo) { + err = nla_put(skb, XFRMA_OFFLOAD_DEV, sizeof(*m->xuo), m->xuo); + if (err) + goto out_cancel; + } + + if (m->new_mark) { + err = nla_put(skb, XFRMA_MARK, sizeof(*m->new_mark), + m->new_mark); + if (err) + goto out_cancel; + } + + err = xfrm_smark_put(skb, &m->smark); + if (err) + goto out_cancel; + + if (m->mapping_maxage) { + err = nla_put_u32(skb, XFRMA_MTIMER_THRESH, m->mapping_maxage); + if (err) + goto out_cancel; + } + + if (m->nat_keepalive_interval) { + err = nla_put_u32(skb, XFRMA_NAT_KEEPALIVE_INTERVAL, + m->nat_keepalive_interval); + if (err) + goto out_cancel; + } + + if (dir) { + err = nla_put_u8(skb, XFRMA_SA_DIR, dir); + if (err) + goto out_cancel; + } + + nlmsg_end(skb, nlh); + return 0; + +out_cancel: + nlmsg_cancel(skb, nlh); + return err; +} + +static unsigned int xfrm_migrate_state_msgsize(const struct xfrm_migrate *m, + u8 dir) +{ + return NLMSG_ALIGN(sizeof(struct xfrm_user_migrate_state)) + + (m->encap ? nla_total_size(sizeof(struct xfrm_encap_tmpl)) : 0) + + (m->xuo ? nla_total_size(sizeof(struct xfrm_user_offload)) : 0) + + (m->new_mark ? nla_total_size(sizeof(struct xfrm_mark)) : 0) + + ((m->smark.v | m->smark.m) ? nla_total_size(sizeof(u32)) * 2 : 0) + + (m->mapping_maxage ? nla_total_size(sizeof(u32)) : 0) + + (m->nat_keepalive_interval ? nla_total_size(sizeof(u32)) : 0) + + (dir ? nla_total_size(sizeof(u8)) : 0); /* XFRMA_SA_DIR */ +} + +static int xfrm_send_migrate_state(struct net *net, + const struct xfrm_user_migrate_state *um, + const struct xfrm_migrate *m, + u8 dir, u32 portid, u32 seq) +{ + int err; + struct sk_buff *skb; + + skb = nlmsg_new(xfrm_migrate_state_msgsize(m, dir), GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + err = build_migrate_state(skb, um, m, dir, portid, seq); + if (err < 0) { + kfree_skb(skb); + return err; + } + + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE); +} + +static int xfrm_do_migrate_state(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs, struct netlink_ext_ack *extack) +{ + struct xfrm_user_migrate_state *um = nlmsg_data(nlh); + struct net *net = sock_net(skb->sk); + struct xfrm_user_offload xuo = {}; + struct xfrm_migrate m = {}; + struct xfrm_state *xc; + struct xfrm_state *x; + int err; + + if (!um->id.spi) { + NL_SET_ERR_MSG(extack, "Invalid SPI 0x0"); + return -EINVAL; + } + + if (um->reserved) { + NL_SET_ERR_MSG(extack, "Reserved field must be zero"); + return -EINVAL; + } + + if (um->flags & ~XFRM_MIGRATE_STATE_KNOWN_FLAGS) { + NL_SET_ERR_MSG_FMT(extack, "Unknown flags: 0x%x", + um->flags & ~XFRM_MIGRATE_STATE_KNOWN_FLAGS); + return -EINVAL; + } + + err = verify_xfrm_family(um->new_family, extack); + if (err) + return err; + + if (!(um->flags & XFRM_MIGRATE_STATE_UPDATE_H2H_SEL)) { + err = verify_selector_prefixlen(um->new_sel.family, + &um->new_sel, extack); + if (err) + return err; + } + + copy_from_user_migrate_state(&m, um); + + x = xfrm_state_lookup(net, m.old_mark.v & m.old_mark.m, + &um->id.daddr, um->id.spi, + um->id.proto, um->id.family); + if (!x) { + NL_SET_ERR_MSG(extack, "Can not find state"); + return -ESRCH; + } + + if (um->flags & XFRM_MIGRATE_STATE_UPDATE_H2H_SEL) { + u8 prefixlen = (x->props.family == AF_INET6) ? 128 : 32; + + if (x->sel.prefixlen_s != x->sel.prefixlen_d || + x->sel.prefixlen_d != prefixlen || + !xfrm_addr_equal(&x->sel.daddr, &x->id.daddr, x->props.family) || + !xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) { + NL_SET_ERR_MSG(extack, + "SA selector is not a single-host match for SA addresses"); + err = -EINVAL; + goto out; + } + } + + if (attrs[XFRMA_ENCAP]) { + m.encap = nla_data(attrs[XFRMA_ENCAP]); + if (m.encap->encap_type == 0) { + m.encap = NULL; /* sentinel: remove encap */ + } else if (m.encap->encap_type != UDP_ENCAP_ESPINUDP) { + NL_SET_ERR_MSG(extack, "Unsupported encapsulation type"); + err = -EINVAL; + goto out; + } + } else { + m.encap = x->encap; /* omit-to-inherit */ + } + + if (attrs[XFRMA_MTIMER_THRESH]) { + err = verify_mtimer_thresh(!!m.encap, x->dir, extack); + if (err) + goto out; + } + + if (nla_get_u32_default(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL], 0) && !m.encap) { + NL_SET_ERR_MSG(extack, + "NAT_KEEPALIVE_INTERVAL requires encapsulation"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_OFFLOAD_DEV]) { + m.xuo = nla_data(attrs[XFRMA_OFFLOAD_DEV]); + } else { + bool inherit_offload = !(um->flags & XFRM_MIGRATE_STATE_CLEAR_OFFLOAD); + + if (inherit_offload && x->xso.dev) { + xso_to_xuo(&x->xso, &xuo); + m.xuo = &xuo; + } + } + + if (attrs[XFRMA_MARK]) + m.new_mark = nla_data(attrs[XFRMA_MARK]); + + if (attrs[XFRMA_SET_MARK]) + xfrm_smark_init(attrs, &m.smark); + else + m.smark = x->props.smark; + + m.mapping_maxage = nla_get_u32_default(attrs[XFRMA_MTIMER_THRESH], + x->mapping_maxage); + m.nat_keepalive_interval = nla_get_u32_default(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL], + x->nat_keepalive_interval); + + if (m.new_family != um->id.family || + !xfrm_addr_equal(&m.new_daddr, &um->id.daddr, um->id.family)) { + u32 new_mark_key = m.new_mark ? m.new_mark->v & m.new_mark->m : + m.old_mark.v & m.old_mark.m; + struct xfrm_state *x_new; + + x_new = xfrm_state_lookup(net, new_mark_key, &m.new_daddr, + um->id.spi, um->id.proto, m.new_family); + if (x_new) { + xfrm_state_put(x_new); + NL_SET_ERR_MSG(extack, "New SA tuple already occupied"); + err = -EEXIST; + goto out; + } + } + + xc = xfrm_state_migrate_create(x, &m, net, extack); + if (!xc) { + NL_SET_ERR_MSG_WEAK(extack, "State migration clone failed"); + err = -EINVAL; + goto out; + } + + spin_lock_bh(&x->lock); + if (x->km.state != XFRM_STATE_VALID) { + spin_unlock_bh(&x->lock); + NL_SET_ERR_MSG(extack, "State already deleted"); + err = -ESRCH; + goto out_xc; + } + xfrm_migrate_sync(xc, x); /* to prevent SN/IV reuse */ + __xfrm_state_delete(x); + spin_unlock_bh(&x->lock); + + err = xfrm_state_migrate_install(x, xc, &m, extack); + if (err < 0) { + /* + * Should not occur: pre-check above ensures the new tuple is + * free under xfrm_cfg_mutex. Both SAs are gone if it does; + * restoring x would risk SN/IV reuse. + */ + goto out; + } + + /* Restore encap cleared by sentinel (type=0) during migration. */ + if (attrs[XFRMA_ENCAP]) + m.encap = nla_data(attrs[XFRMA_ENCAP]); + + m.new_sel = &xc->sel; + m.mapping_maxage = xc->mapping_maxage; + m.nat_keepalive_interval = xc->nat_keepalive_interval; + + err = xfrm_send_migrate_state(net, um, &m, xc->dir, + nlh->nlmsg_pid, nlh->nlmsg_seq); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Failed to send migration notification"); + err = 0; + } + +out: + xfrm_state_put(x); + return err; +out_xc: + xc->km.state = XFRM_STATE_DEAD; + xfrm_state_put(xc); + xfrm_state_put(x); + return err; +} + #else +static int xfrm_do_migrate_state(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs, struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "XFRM_MSG_MIGRATE_STATE is not supported"); + return -ENOPROTOOPT; +} + static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { @@ -3345,6 +3662,7 @@ const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default), [XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default), + [XFRM_MSG_MIGRATE_STATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_migrate_state), }; EXPORT_SYMBOL_GPL(xfrm_msg_min); @@ -3438,6 +3756,7 @@ static const struct xfrm_link { [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = { .doit = xfrm_get_spdinfo }, [XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_set_default }, [XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_get_default }, + [XFRM_MSG_MIGRATE_STATE - XFRM_MSG_BASE] = { .doit = xfrm_do_migrate_state }, }; static int xfrm_reject_unused_attr(int type, struct nlattr **attrs, diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 2c0b07f9fbbd..655d2616c9d2 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -128,6 +128,7 @@ static const struct nlmsg_perm nlmsg_xfrm_perms[] = { { XFRM_MSG_MAPPING, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_SETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_READ }, + { XFRM_MSG_MIGRATE_STATE, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, }; static const struct nlmsg_perm nlmsg_audit_perms[] = { @@ -203,7 +204,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) * structures at the top of this file with the new mappings * before updating the BUILD_BUG_ON() macro! */ - BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_GETDEFAULT); + BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_MIGRATE_STATE); if (selinux_policycap_netlink_xperm()) { *perm = NETLINK_XFRM_SOCKET__NLMSG; -- cgit v1.3-14-g43fede From f3ff3eb0d6a4080fa7f554b8478a3405b8e4befe Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 4 Jun 2026 21:58:31 +0200 Subject: batman-adv: uapi: keep kernel-doc in struct member order The order of the members of struct batadv_coded_packet and struct batadv_unicast_tvlv_packet didn't match the kernel doc. This is the case for all other structures and should also be done the same way for these two. Signed-off-by: Sven Eckelmann --- include/uapi/linux/batadv_packet.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 439132a819ea..1241285b866c 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -518,16 +518,16 @@ struct batadv_mcast_packet { * @packet_type: batman-adv packet type, part of the general header * @version: batman-adv protocol version, part of the general header * @ttl: time to live for this packet, part of the general header + * @first_ttvn: tt-version number of first included packet * @first_source: original source of first included packet * @first_orig_dest: original destination of first included packet * @first_crc: checksum of first included packet - * @first_ttvn: tt-version number of first included packet * @second_ttl: ttl of second packet + * @second_ttvn: tt version number of second included packet * @second_dest: second receiver of this coded packet * @second_source: original source of second included packet * @second_orig_dest: original destination of second included packet * @second_crc: checksum of second included packet - * @second_ttvn: tt version number of second included packet * @coded_len: length of network coded part of the payload */ struct batadv_coded_packet { @@ -554,8 +554,8 @@ struct batadv_coded_packet { * @version: batman-adv protocol version, part of the general header * @ttl: time to live for this packet, part of the general header * @reserved: reserved field (for packet alignment) - * @src: address of the source * @dst: address of the destination + * @src: address of the source * @tvlv_len: length of tvlv data following the unicast tvlv header * @align: 2 bytes to align the header to a 4 byte boundary */ -- cgit v1.3-14-g43fede From 16b4d3e2fb24aac3e68a8d86e3bc5e302e1b5cb7 Mon Sep 17 00:00:00 2001 From: Mykyta Yatsenko Date: Fri, 5 Jun 2026 04:41:21 -0700 Subject: bpf: Implement resizable hashmap basic functions Use rhashtable_lookup_likely() for lookups, rhashtable_remove_fast() for deletes, and rhashtable_lookup_get_insert_fast() for inserts. Updates modify values in place under RCU rather than allocating a new element and swapping the pointer (as regular htab does). This trades read consistency for performance: concurrent readers may see partial updates. BPF_F_LOCK support and special-field handling (timers, kptrs, etc.) follow in a later commit. Initialize rhashtable with bpf_mem_alloc element cache. Require BPF_F_NO_PREALLOC. Limit max_entries to 2^31. Free elements via rhashtable_free_and_destroy(). Signed-off-by: Mykyta Yatsenko Link: https://lore.kernel.org/r/20260605-rhash-v7-4-5b8e05f8630d@meta.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 6 + kernel/bpf/hashtab.c | 311 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 3 + kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 6 + 6 files changed, 328 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b13de31e163f..56e4c3f983d3 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -134,6 +134,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_USER_RINGBUF, user_ringbuf_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_ARENA, arena_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_INSN_ARRAY, insn_array_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_RHASH, rhtab_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index aec171ccb6ef..bed9b1b4d5ef 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1047,6 +1047,7 @@ enum bpf_map_type { BPF_MAP_TYPE_CGRP_STORAGE, BPF_MAP_TYPE_ARENA, BPF_MAP_TYPE_INSN_ARRAY, + BPF_MAP_TYPE_RHASH, __MAX_BPF_MAP_TYPE }; @@ -1545,6 +1546,11 @@ union bpf_attr { * * BPF_MAP_TYPE_ARENA - contains the address where user space * is going to mmap() the arena. It has to be page aligned. + * + * BPF_MAP_TYPE_RHASH - initial table size hint + * (nelem_hint). 0 = use rhashtable default. Must be + * <= min(max_entries, U16_MAX). Upper 32 bits reserved, + * must be zero. */ __u64 map_extra; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3dd9b4924ae4..10f3a058747b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -2739,3 +2740,313 @@ const struct bpf_map_ops htab_of_maps_map_ops = { BATCH_OPS(htab), .map_btf_id = &htab_map_btf_ids[0], }; + +struct rhtab_elem { + struct rhash_head node; + /* key bytes, then value bytes follow */ + u8 data[] __aligned(8); +}; + +struct bpf_rhtab { + struct bpf_map map; + struct rhashtable ht; + struct bpf_mem_alloc ma; + u32 elem_size; +}; + +static const struct rhashtable_params rhtab_params = { + .head_offset = offsetof(struct rhtab_elem, node), + .key_offset = offsetof(struct rhtab_elem, data), +}; + +static inline void *rhtab_elem_value(struct rhtab_elem *l, u32 key_size) +{ + return l->data + round_up(key_size, 8); +} + +static struct bpf_map *rhtab_map_alloc(union bpf_attr *attr) +{ + struct rhashtable_params params; + struct bpf_rhtab *rhtab; + int err = 0; + + rhtab = bpf_map_area_alloc(sizeof(*rhtab), NUMA_NO_NODE); + if (!rhtab) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&rhtab->map, attr); + + if (rhtab->map.max_entries > 1UL << 31) { + err = -E2BIG; + goto free_rhtab; + } + + rhtab->elem_size = sizeof(struct rhtab_elem) + round_up(rhtab->map.key_size, 8) + + round_up(rhtab->map.value_size, 8); + + params = rhtab_params; + params.key_len = rhtab->map.key_size; + params.nelem_hint = (u32)attr->map_extra; + params.automatic_shrinking = true; + + err = rhashtable_init(&rhtab->ht, ¶ms); + if (err) + goto free_rhtab; + + /* Set max_elems after rhashtable_init() since init zeroes the struct */ + rhtab->ht.max_elems = rhtab->map.max_entries; + + err = bpf_mem_alloc_init(&rhtab->ma, rhtab->elem_size, false); + if (err) + goto destroy_rhtab; + + return &rhtab->map; + +destroy_rhtab: + rhashtable_destroy(&rhtab->ht); +free_rhtab: + bpf_map_area_free(rhtab); + return ERR_PTR(err); +} + +static int rhtab_map_alloc_check(union bpf_attr *attr) +{ + if (!(attr->map_flags & BPF_F_NO_PREALLOC)) + return -EINVAL; + + if (attr->map_flags & BPF_F_ZERO_SEED) + return -EINVAL; + + if (attr->key_size > U16_MAX) + return -E2BIG; + + if (attr->map_extra >> 32) + return -EINVAL; + + if ((u32)attr->map_extra > U16_MAX) + return -E2BIG; + + if ((u32)attr->map_extra > attr->max_entries) + return -EINVAL; + + return htab_map_alloc_check(attr); +} + +static void rhtab_free_elem(void *ptr, void *arg) +{ + struct bpf_rhtab *rhtab = arg; + struct rhtab_elem *elem = ptr; + + bpf_mem_cache_free_rcu(&rhtab->ma, elem); +} + +static void rhtab_map_free(struct bpf_map *map) +{ + struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); + + rhashtable_free_and_destroy(&rhtab->ht, rhtab_free_elem, rhtab); + bpf_mem_alloc_destroy(&rhtab->ma); + bpf_map_area_free(rhtab); +} + +static void *rhtab_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); + + /* Hold RCU lock in case sleepable program calls via gen_lookup */ + guard(rcu)(); + + return rhashtable_lookup_likely(&rhtab->ht, key, rhtab_params); +} + +static void *rhtab_map_lookup_elem(struct bpf_map *map, void *key) __must_hold(RCU) +{ + struct rhtab_elem *l; + + l = rhtab_lookup_elem(map, key); + return l ? rhtab_elem_value(l, map->key_size) : NULL; +} + +static void rhtab_read_elem_value(struct bpf_map *map, void *dst, struct rhtab_elem *elem, + u64 flags) +{ + void *src = rhtab_elem_value(elem, map->key_size); + + if (flags & BPF_F_LOCK) + copy_map_value_locked(map, dst, src, true); + else + copy_map_value(map, dst, src); +} + +static int rhtab_delete_elem(struct bpf_rhtab *rhtab, struct rhtab_elem *elem, void *copy, + u64 flags) +{ + int err; + + /* + * disable_instrumentation() mitigates the deadlock for programs running in NMI context. + * rhashtable locks bucket with local_irq_save(). Only NMI programs may reenter + * rhashtable code, bpf_disable_instrumentation() disables programs running in NMI, except + * raw tracepoints, which we don't have in rhashtable. + */ + bpf_disable_instrumentation(); + err = rhashtable_remove_fast(&rhtab->ht, &elem->node, rhtab_params); + bpf_enable_instrumentation(); + + if (err) + return err; + + if (copy) { + rhtab_read_elem_value(&rhtab->map, copy, elem, flags); + check_and_init_map_value(&rhtab->map, copy); + } + + bpf_mem_cache_free_rcu(&rhtab->ma, elem); + return 0; +} + + +static long rhtab_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); + struct rhtab_elem *elem; + + guard(rcu)(); + + elem = rhtab_lookup_elem(map, key); + if (!elem) + return -ENOENT; + + return rhtab_delete_elem(rhtab, elem, NULL, 0); +} + +static int rhtab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, void *value, u64 flags) +{ + struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); + struct rhtab_elem *elem; + int err; + + err = bpf_map_check_op_flags(map, flags, BPF_F_LOCK); + if (err) + return err; + + guard(rcu)(); + + elem = rhtab_lookup_elem(map, key); + if (!elem) + return -ENOENT; + + return rhtab_delete_elem(rhtab, elem, value, flags); +} + +static long rhtab_map_update_existing(struct bpf_map *map, struct rhtab_elem *elem, void *value, + u64 map_flags) +{ + void *old_val = rhtab_elem_value(elem, map->key_size); + + if (map_flags & BPF_NOEXIST) + return -EEXIST; + + if (map_flags & BPF_F_LOCK) + copy_map_value_locked(map, old_val, value, false); + else + copy_map_value(map, old_val, value); + return 0; +} + +static long rhtab_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) +{ + struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); + struct rhtab_elem *elem, *tmp; + + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST)) + return -EINVAL; + + if ((map_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) + return -EINVAL; + + guard(rcu)(); + elem = rhtab_lookup_elem(map, key); + if (elem) + return rhtab_map_update_existing(map, elem, value, map_flags); + + if (map_flags & BPF_EXIST) + return -ENOENT; + + /* Check max_entries limit before inserting new element */ + if (atomic_read(&rhtab->ht.nelems) >= map->max_entries) + return -E2BIG; + + elem = bpf_mem_cache_alloc(&rhtab->ma); + if (!elem) + return -ENOMEM; + + memcpy(elem->data, key, map->key_size); + copy_map_value(map, rhtab_elem_value(elem, map->key_size), value); + + /* Prevent deadlock for NMI programs attempting to take bucket lock */ + bpf_disable_instrumentation(); + tmp = rhashtable_lookup_get_insert_fast(&rhtab->ht, &elem->node, rhtab_params); + bpf_enable_instrumentation(); + + if (tmp) { + bpf_mem_cache_free(&rhtab->ma, elem); + if (IS_ERR(tmp)) + return PTR_ERR(tmp); + + return rhtab_map_update_existing(map, tmp, value, map_flags); + } + + return 0; +} + +static int rhtab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + + BUILD_BUG_ON(!__same_type(&rhtab_lookup_elem, + (void *(*)(struct bpf_map *map, void *key)) NULL)); + *insn++ = BPF_EMIT_CALL(rhtab_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); + *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, + offsetof(struct rhtab_elem, data) + round_up(map->key_size, 8)); + + return insn - insn_buf; +} + +static void rhtab_map_free_internal_structs(struct bpf_map *map) +{ +} + +static int rhtab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EOPNOTSUPP; +} + +static u64 rhtab_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); + u64 num_entries; + + /* Excludes rhashtable bucket overhead (~ nelems * sizeof(void *) at 75% load). */ + num_entries = atomic_read(&rhtab->ht.nelems); + return sizeof(struct bpf_rhtab) + rhtab->elem_size * num_entries; +} + +BTF_ID_LIST_SINGLE(rhtab_map_btf_ids, struct, bpf_rhtab) +const struct bpf_map_ops rhtab_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = rhtab_map_alloc_check, + .map_alloc = rhtab_map_alloc, + .map_free = rhtab_map_free, + .map_get_next_key = rhtab_map_get_next_key, + .map_release_uref = rhtab_map_free_internal_structs, + .map_lookup_elem = rhtab_map_lookup_elem, + .map_lookup_and_delete_elem = rhtab_map_lookup_and_delete_elem, + .map_update_elem = rhtab_map_update_elem, + .map_delete_elem = rhtab_map_delete_elem, + .map_gen_lookup = rhtab_map_gen_lookup, + .map_mem_usage = rhtab_map_mem_usage, + .map_btf_id = &rhtab_map_btf_ids[0], +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 625a4366fe6d..1faae184de48 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1398,6 +1398,7 @@ static int map_create_alloc(union bpf_attr *attr, bpfptr_t uattr, struct bpf_ver if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && attr->map_type != BPF_MAP_TYPE_ARENA && + attr->map_type != BPF_MAP_TYPE_RHASH && attr->map_extra != 0) { bpf_log(log, "Invalid map_extra.\n"); return -EINVAL; @@ -1469,6 +1470,7 @@ static int map_create_alloc(union bpf_attr *attr, bpfptr_t uattr, struct bpf_ver case BPF_MAP_TYPE_CGROUP_ARRAY: case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_RHASH: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_RINGBUF: @@ -2259,6 +2261,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_RHASH || map->map_type == BPF_MAP_TYPE_STACK_TRACE) { if (!bpf_map_is_offloaded(map)) { bpf_disable_instrumentation(); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8ed484cb1a8a..7d27ba396d32 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -17657,6 +17657,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, if (prog->sleepable) switch (map->map_type) { case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_RHASH: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_HASH: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 37142e6d911a..7d0b282ba674 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1047,6 +1047,7 @@ enum bpf_map_type { BPF_MAP_TYPE_CGRP_STORAGE, BPF_MAP_TYPE_ARENA, BPF_MAP_TYPE_INSN_ARRAY, + BPF_MAP_TYPE_RHASH, __MAX_BPF_MAP_TYPE }; @@ -1545,6 +1546,11 @@ union bpf_attr { * * BPF_MAP_TYPE_ARENA - contains the address where user space * is going to mmap() the arena. It has to be page aligned. + * + * BPF_MAP_TYPE_RHASH - initial table size hint + * (nelem_hint). 0 = use rhashtable default. Must be + * <= min(max_entries, U16_MAX). Upper 32 bits reserved, + * must be zero. */ __u64 map_extra; -- cgit v1.3-14-g43fede From 682ecb14e83840e87ea36c6d7c16c5111ce18784 Mon Sep 17 00:00:00 2001 From: Ankit Agrawal Date: Tue, 2 Jun 2026 06:30:15 +0000 Subject: vfio/nvgrace-gpu: Add Blackwell-Next GPU readiness check via CXL DVSEC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a CXL DVSEC-based readiness check for Blackwell-Next GPUs alongside the existing legacy BAR0 polling path. The CXL Device DVSEC offset is discovered at probe time. Probe, fault and read/write paths then branch on that to use either the legacy BAR0 polling or the CXL DVSEC polling. The CXL path polls Memory_Active, requiring MEM_INFO_VALID within 1s and MEM_ACTIVE within Memory_Active_Timeout (up to 256s) as per CXL spec r4.0 sec 8.1.3.8.2. Given the long worst-case wait, the CXL poll runs outside memory_lock with only a quick readiness check is done under the lock. The poll loops sleep with schedule_timeout_killable() and return -EINTR on a fatal signal. This avoids hung-task panics during the long uninterruptible wait. Extend this to the legacy based wait as well for improvement. In the fault handler the wait runs locklessly before memory_lock. If a reset races in, the in-lock recheck returns -EAGAIN and the wait is retried rather than returning a spurious VM_FAULT_SIGBUS. Add PCI_DVSEC_CXL_MEM_ACTIVE_TIMEOUT to pci_regs.h for the timeout field. Cc: Ilpo Järvinen Cc: Kevin Tian Suggested-by: Alex Williamson Signed-off-by: Ankit Agrawal Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20260602063015.3915-1-ankita@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/pci/nvgrace-gpu/main.c | 162 +++++++++++++++++++++++++++++++++--- include/uapi/linux/pci_regs.h | 1 + 2 files changed, 151 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index 15e2f03c6cd4..d07dcacb76bd 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -3,10 +3,13 @@ * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved */ +#include #include +#include #include #include #include +#include #include #include #include @@ -65,6 +68,8 @@ struct nvgrace_gpu_pci_core_device { bool has_mig_hw_bug; /* GPU has just been reset */ bool reset_done; + /* CXL Device DVSEC offset; 0 if not present (legacy GB path) */ + int cxl_dvsec; }; static void nvgrace_gpu_init_fake_bar_emu_regs(struct vfio_device *core_vdev) @@ -248,7 +253,7 @@ static void nvgrace_gpu_close_device(struct vfio_device *core_vdev) vfio_pci_core_close_device(core_vdev); } -static int nvgrace_gpu_wait_device_ready(void __iomem *io) +static int nvgrace_gpu_wait_device_ready_legacy(void __iomem *io) { unsigned long timeout = jiffies + msecs_to_jiffies(POLL_TIMEOUT_MS); @@ -256,16 +261,97 @@ static int nvgrace_gpu_wait_device_ready(void __iomem *io) if ((ioread32(io + C2C_LINK_BAR0_OFFSET) == STATUS_READY) && (ioread32(io + HBM_TRAINING_BAR0_OFFSET) == STATUS_READY)) return 0; - msleep(POLL_QUANTUM_MS); + if (schedule_timeout_killable(msecs_to_jiffies(POLL_QUANTUM_MS))) + return -EINTR; } while (!time_after(jiffies, timeout)); return -ETIME; } +/* + * Decode the 3-bit Memory_Active_Timeout field from CXL DVSEC Range 1 Low + * (bits 15:13) into milliseconds. Encoding per CXL spec r4.0 sec 8.1.3.8.2: + * 000b = 1s, 001b = 4s, 010b = 16s, 011b = 64s, 100b = 256s, + * 101b-111b = reserved (clamped to 256s). + */ +static inline unsigned long cxl_mem_active_timeout_ms(u8 timeout) +{ + return MSEC_PER_SEC << (2 * min_t(u8, timeout, 4)); +} + +/* + * Check if CXL DVSEC reports memory as valid and active. + */ +static inline bool cxl_dvsec_mem_is_active(u32 status) +{ + return (status & PCI_DVSEC_CXL_MEM_INFO_VALID) && + (status & PCI_DVSEC_CXL_MEM_ACTIVE); +} + +static int nvgrace_gpu_test_device_ready_cxl(struct nvgrace_gpu_pci_core_device *nvdev, + u32 *status) +{ + struct pci_dev *pdev = nvdev->core_device.pdev; + int cxl_dvsec = nvdev->cxl_dvsec; + u32 val; + + pci_read_config_dword(pdev, + cxl_dvsec + PCI_DVSEC_CXL_RANGE_SIZE_LOW(0), + &val); + + if (val == ~0U) + return -ENODEV; + + if (status) + *status = val; + + if (cxl_dvsec_mem_is_active(val)) + return 0; + + return -EAGAIN; +} + +/* + * As per CXL spec r4.0 sec 8.1.3.8.2, MEM_INFO_VALID needs to be set + * within 1s and MEM_ACTIVE within Memory_Active_Timeout (up to ~256s) + * after reset and bootup. + */ +static int nvgrace_gpu_wait_device_ready_cxl(struct nvgrace_gpu_pci_core_device *nvdev) +{ + unsigned long deadline = jiffies + msecs_to_jiffies(POLL_QUANTUM_MS); + bool active_phase = false; + u32 status; + int ret; + + for (;;) { + ret = nvgrace_gpu_test_device_ready_cxl(nvdev, &status); + if (ret != -EAGAIN) + return ret; + + if (!active_phase && (status & PCI_DVSEC_CXL_MEM_INFO_VALID)) { + u8 t = FIELD_GET(PCI_DVSEC_CXL_MEM_ACTIVE_TIMEOUT, status); + + deadline = jiffies + + msecs_to_jiffies(cxl_mem_active_timeout_ms(t)); + active_phase = true; + } + + if (time_after(jiffies, deadline)) + return -ETIME; + + if (schedule_timeout_killable(msecs_to_jiffies(POLL_QUANTUM_MS))) + return -EINTR; + } +} + /* * If the GPU memory is accessed by the CPU while the GPU is not ready * after reset, it can cause harmless corrected RAS events to be logged. * Make sure the GPU is ready before establishing the mappings. + * + * Since the CXL polling wait could take 256s, it happens outside + * memory_lock. Only do quick readiness check under the lock. Legacy + * keeps the in-lock poll. */ static int nvgrace_gpu_check_device_ready(struct nvgrace_gpu_pci_core_device *nvdev) @@ -281,7 +367,10 @@ nvgrace_gpu_check_device_ready(struct nvgrace_gpu_pci_core_device *nvdev) if (!__vfio_pci_memory_enabled(vdev)) return -EIO; - ret = nvgrace_gpu_wait_device_ready(nvdev->bar0_base); + if (nvdev->cxl_dvsec) + ret = nvgrace_gpu_test_device_ready_cxl(nvdev, NULL); + else + ret = nvgrace_gpu_wait_device_ready_legacy(nvdev->bar0_base); if (ret) return ret; @@ -319,9 +408,33 @@ static vm_fault_t nvgrace_gpu_vfio_pci_huge_fault(struct vm_fault *vmf, pfn = PHYS_PFN(memregion->memphys) + addr_to_pgoff(vma, addr); if (is_aligned_for_order(vma, addr, pfn, order)) { + /* + * Exit early under memory_lock to avoid a potentially lengthy + * device readiness wait on a runtime-suspended device. Any + * race after the lock is dropped is benign as the re-check + * inside the scoped guard below catches it. + */ + scoped_guard(rwsem_read, &vdev->memory_lock) { + if (vdev->pm_runtime_engaged) + return VM_FAULT_SIGBUS; + } + +retry: + if (nvdev->cxl_dvsec && READ_ONCE(nvdev->reset_done) && + nvgrace_gpu_wait_device_ready_cxl(nvdev)) + return VM_FAULT_SIGBUS; + scoped_guard(rwsem_read, &vdev->memory_lock) { - if (vdev->pm_runtime_engaged || - nvgrace_gpu_check_device_ready(nvdev)) + int rc; + + if (vdev->pm_runtime_engaged) + return VM_FAULT_SIGBUS; + + /* Re-run the wait if a reset raced us, not SIGBUS. */ + rc = nvgrace_gpu_check_device_ready(nvdev); + if (rc == -EAGAIN) + goto retry; + if (rc) return VM_FAULT_SIGBUS; ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order); @@ -718,6 +831,12 @@ nvgrace_gpu_read_mem(struct nvgrace_gpu_pci_core_device *nvdev, else mem_count = min(count, memregion->memlength - (size_t)offset); + if (nvdev->cxl_dvsec && READ_ONCE(nvdev->reset_done)) { + ret = nvgrace_gpu_wait_device_ready_cxl(nvdev); + if (ret) + return ret; + } + scoped_guard(rwsem_read, &vdev->memory_lock) { ret = nvgrace_gpu_check_device_ready(nvdev); if (ret) @@ -852,6 +971,12 @@ nvgrace_gpu_write_mem(struct nvgrace_gpu_pci_core_device *nvdev, */ mem_count = min(count, memregion->memlength - (size_t)offset); + if (nvdev->cxl_dvsec && READ_ONCE(nvdev->reset_done)) { + ret = nvgrace_gpu_wait_device_ready_cxl(nvdev); + if (ret) + return ret; + } + scoped_guard(rwsem_read, &vdev->memory_lock) { ret = nvgrace_gpu_check_device_ready(nvdev); if (ret) @@ -1149,14 +1274,24 @@ static bool nvgrace_gpu_has_mig_hw_bug(struct pci_dev *pdev) * is beneficial to make the check to ensure the device is in an * expected state. * - * Ensure that the BAR0 region is enabled before accessing the + * On Blackwell-Next systems, memory readiness is determined via the + * CXL Device DVSEC in PCI config space and does not require BAR0. + * For the legacy path, ensure BAR0 is enabled before accessing the * registers. */ -static int nvgrace_gpu_probe_check_device_ready(struct pci_dev *pdev) +static int nvgrace_gpu_probe_check_device_ready(struct nvgrace_gpu_pci_core_device *nvdev) { + struct pci_dev *pdev = nvdev->core_device.pdev; void __iomem *io; int ret; + /* + * Note that the worst-case wait here is ~256s (vs ~30s on the + * legacy path) and may block device unbind/sysfs for the duration. + */ + if (nvdev->cxl_dvsec) + return nvgrace_gpu_wait_device_ready_cxl(nvdev); + ret = pci_enable_device(pdev); if (ret) return ret; @@ -1171,7 +1306,7 @@ static int nvgrace_gpu_probe_check_device_ready(struct pci_dev *pdev) goto iomap_exit; } - ret = nvgrace_gpu_wait_device_ready(io); + ret = nvgrace_gpu_wait_device_ready_legacy(io); pci_iounmap(pdev, io); iomap_exit: @@ -1189,10 +1324,6 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev, u64 memphys, memlength; int ret; - ret = nvgrace_gpu_probe_check_device_ready(pdev); - if (ret) - return ret; - ret = nvgrace_gpu_fetch_memory_property(pdev, &memphys, &memlength); if (!ret) ops = &nvgrace_gpu_pci_ops; @@ -1202,6 +1333,13 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev, if (IS_ERR(nvdev)) return PTR_ERR(nvdev); + nvdev->cxl_dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL, + PCI_DVSEC_CXL_DEVICE); + + ret = nvgrace_gpu_probe_check_device_ready(nvdev); + if (ret) + goto out_put_vdev; + dev_set_drvdata(&pdev->dev, &nvdev->core_device); if (ops == &nvgrace_gpu_pci_ops) { diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 14f634ab9350..718fb630f5bb 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1357,6 +1357,7 @@ #define PCI_DVSEC_CXL_RANGE_SIZE_LOW(i) (0x1C + (i * 0x10)) #define PCI_DVSEC_CXL_MEM_INFO_VALID _BITUL(0) #define PCI_DVSEC_CXL_MEM_ACTIVE _BITUL(1) +#define PCI_DVSEC_CXL_MEM_ACTIVE_TIMEOUT __GENMASK(15, 13) #define PCI_DVSEC_CXL_MEM_SIZE_LOW __GENMASK(31, 28) #define PCI_DVSEC_CXL_RANGE_BASE_HIGH(i) (0x20 + (i * 0x10)) #define PCI_DVSEC_CXL_RANGE_BASE_LOW(i) (0x24 + (i * 0x10)) -- cgit v1.3-14-g43fede From e2a49fdb1beed150125b4104c90eb2a96ec7f63a Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Fri, 5 Jun 2026 23:52:47 +0800 Subject: bpf: Check tail zero of bpf_map_info Since there're 4 bytes padding at the end of struct bpf_map_info, they won't be checked by bpf_check_uarg_tail_zero(). pahole -C bpf_map_info ./vmlinux struct bpf_map_info { ... __u64 hash __attribute__((__aligned__(8))); /* 88 8 */ __u32 hash_size; /* 96 4 */ /* size: 104, cachelines: 2, members: 18 */ /* padding: 4 */ /* forced alignments: 1 */ /* last cacheline: 40 bytes */ } __attribute__((__aligned__(8))); If a future kernel extension adds a new 4-byte field, older userspace programs allocating this structure on the stack might inadvertently pass uninitialized stack garbage into the new field, permanently breaking backward compatibility. -- sashiko [1] Fix it by changing sizeof(info) to offsetofend(struct bpf_map_info, hash_size). And, add "__u32 :32" to the tail of struct bpf_map_info. [1] https://lore.kernel.org/bpf/20260513224823.6494FC19425@smtp.kernel.org/ Fixes: ea2e6467ac36 ("bpf: Return hashes of maps in BPF_OBJ_GET_INFO_BY_FD") Acked-by: Mykyta Yatsenko Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20260605155249.20772-2-leon.hwang@linux.dev Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 5 +++-- tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bed9b1b4d5ef..e1730f449d9e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6733,6 +6733,7 @@ struct bpf_map_info { __u64 map_extra; __aligned_u64 hash; __u32 hash_size; + __u32 :32; } __attribute__((aligned(8))); struct bpf_btf_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 31a3b70a0b5d..89f020a44fc9 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5406,10 +5406,11 @@ static int bpf_map_get_info_by_fd(struct file *file, { struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_map_info info; - u32 info_len = attr->info.info_len; + u32 info_len = attr->info.info_len, len; int err; - err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); + len = offsetofend(struct bpf_map_info, hash_size); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), len, info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7d0b282ba674..7caf667e86fe 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6733,6 +6733,7 @@ struct bpf_map_info { __u64 map_extra; __aligned_u64 hash; __u32 hash_size; + __u32 :32; } __attribute__((aligned(8))); struct bpf_btf_info { -- cgit v1.3-14-g43fede From 786be2b05980a5828e67fc564ad7517e2adbe9bd Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Fri, 5 Jun 2026 23:52:48 +0800 Subject: bpf: Check tail zero of bpf_prog_info Since there're 4 bytes padding at the end of struct bpf_prog_info, they won't be checked by bpf_check_uarg_tail_zero(). pahole -C bpf_prog_info ./vmlinux struct bpf_prog_info { ... __u32 attach_btf_obj_id; /* 220 4 */ __u32 attach_btf_id; /* 224 4 */ /* size: 232, cachelines: 4, members: 38 */ /* sum members: 224 */ /* sum bitfield members: 1 bits, bit holes: 1, sum bit holes: 31 bits */ /* padding: 4 */ /* forced alignments: 9 */ /* last cacheline: 40 bytes */ } __attribute__((__aligned__(8))); If a future kernel extension adds a new 4-byte field, older userspace programs allocating this structure on the stack might inadvertently pass uninitialized stack garbage into the new field, permanently breaking backward compatibility. -- sashiko [1] Fix it by changing sizeof(info) to offsetofend(struct bpf_prog_info, attach_btf_id). And, add "__u32 :32" to the tail of struct bpf_prog_info. [1] https://lore.kernel.org/bpf/20260513224823.6494FC19425@smtp.kernel.org/ Fixes: aba64c7da983 ("bpf: Add verified_insns to bpf_prog_info and fdinfo") Acked-by: Mykyta Yatsenko Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20260605155249.20772-3-leon.hwang@linux.dev Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 5 +++-- tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e1730f449d9e..d5238df5e5eb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6712,6 +6712,7 @@ struct bpf_prog_info { __u32 verified_insns; __u32 attach_btf_obj_id; __u32 attach_btf_id; + __u32 :32; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 89f020a44fc9..c5d4ae957e87 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5121,10 +5121,11 @@ static int bpf_prog_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; struct bpf_prog_kstats stats; char __user *uinsns; - u32 ulen; + u32 ulen, len; int err; - err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); + len = offsetofend(struct bpf_prog_info, attach_btf_id); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), len, info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7caf667e86fe..3829db087449 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6712,6 +6712,7 @@ struct bpf_prog_info { __u32 verified_insns; __u32 attach_btf_obj_id; __u32 attach_btf_id; + __u32 :32; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.3-14-g43fede From d14e6b4346bf397eca7cb5f4b7b0b8054be632d8 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 6 Jun 2026 14:39:35 +0200 Subject: bpf: Add multi tracing attach types Adding new program attach types multi tracing attachment: BPF_TRACE_FENTRY_MULTI BPF_TRACE_FEXIT_MULTI and their base support in verifier code. Programs with such attach type will use specific link attachment interface coming in following changes. This was suggested by Andrii some (long) time ago and turned out to be easier than having special program flag for that. Bpf programs with such types have 'bpf_multi_func' function set as their attach_btf_id and keep module reference when it's specified by attach_prog_fd. They are also accepted as sleepable programs during verification, and the real validation for specific BTF_IDs/functions will happen during the multi link attachment in following changes. Suggested-by: Andrii Nakryiko Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20260606123955.345967-11-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 5 +++++ include/linux/btf_ids.h | 1 + include/uapi/linux/bpf.h | 2 ++ kernel/bpf/fixups.c | 1 + kernel/bpf/syscall.c | 28 ++++++++++++++++++++++++---- kernel/bpf/trampoline.c | 5 ++++- kernel/bpf/verifier.c | 40 +++++++++++++++++++++++++++++++++++++++- net/bpf/test_run.c | 2 ++ tools/include/uapi/linux/bpf.h | 2 ++ tools/lib/bpf/libbpf.c | 2 ++ 10 files changed, 82 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 428789a9e736..b52dc64ec92d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2113,6 +2113,11 @@ static inline void bpf_prog_put_recursion_context(struct bpf_prog *prog) #endif } +static inline bool is_tracing_multi(enum bpf_attach_type type) +{ + return type == BPF_TRACE_FENTRY_MULTI || type == BPF_TRACE_FEXIT_MULTI; +} + #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) /* This macro helps developer to register a struct_ops type and generate * type information correctly. Developers should use this macro to register diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index af011db39ab3..8b5a9ee92513 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -284,5 +284,6 @@ extern u32 bpf_cgroup_btf_id[]; extern u32 bpf_local_storage_map_btf_id[]; extern u32 btf_bpf_map_id[]; extern u32 bpf_kmem_cache_btf_id[]; +extern u32 bpf_multi_func_btf_id[]; #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d5238df5e5eb..28d127e5040a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1156,6 +1156,8 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_SESSION, BPF_TRACE_UPROBE_SESSION, BPF_TRACE_FSESSION, + BPF_TRACE_FENTRY_MULTI, + BPF_TRACE_FEXIT_MULTI, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c index 5aa3f7d99ac9..0cf9735929f5 100644 --- a/kernel/bpf/fixups.c +++ b/kernel/bpf/fixups.c @@ -2186,6 +2186,7 @@ patch_map_ops_generic: insn->imm == BPF_FUNC_get_func_ret) { if (eatype == BPF_TRACE_FEXIT || eatype == BPF_TRACE_FSESSION || + eatype == BPF_TRACE_FEXIT_MULTI || eatype == BPF_MODIFY_RETURN) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0cfc8bcb3dc9..efdd6639a598 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -2719,7 +2720,8 @@ static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, struct btf *attach_btf, u32 btf_id, - struct bpf_prog *dst_prog) + struct bpf_prog *dst_prog, + bool multi_func) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) @@ -2739,6 +2741,14 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, } } + if (multi_func) { + if (prog_type != BPF_PROG_TYPE_TRACING) + return -EINVAL; + if (!attach_btf || btf_id) + return -EINVAL; + return 0; + } + if (attach_btf && (!btf_id || dst_prog)) return -EINVAL; @@ -2946,6 +2956,11 @@ static int bpf_prog_mark_insn_arrays_ready(struct bpf_prog *prog) return 0; } +extern int bpf_multi_func(void); +int __init __used bpf_multi_func(void) { return 0; } + +BTF_ID_LIST_GLOBAL_SINGLE(bpf_multi_func_btf_id, func, bpf_multi_func) + /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD keyring_id @@ -2958,6 +2973,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, struct bpf_log_at bool bpf_cap; int err; char license[128]; + bool multi_func; if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; @@ -3024,6 +3040,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, struct bpf_log_at if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) goto put_token; + multi_func = is_tracing_multi(attr->expected_attach_type); + /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is */ @@ -3045,7 +3063,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, struct bpf_log_at goto put_token; } } - } else if (attr->attach_btf_id) { + } else if (attr->attach_btf_id || multi_func) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); if (IS_ERR(attach_btf)) { @@ -3061,7 +3079,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, struct bpf_log_at if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, - dst_prog)) { + dst_prog, multi_func)) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) @@ -3084,7 +3102,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, struct bpf_log_at prog->expected_attach_type = attr->expected_attach_type; prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE); prog->aux->attach_btf = attach_btf; - prog->aux->attach_btf_id = attr->attach_btf_id; + prog->aux->attach_btf_id = multi_func ? bpf_multi_func_btf_id[0] : attr->attach_btf_id; prog->aux->dst_prog = dst_prog; prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; @@ -4480,6 +4498,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: + case BPF_TRACE_FENTRY_MULTI: + case BPF_TRACE_FEXIT_MULTI: case BPF_MODIFY_RETURN: return BPF_PROG_TYPE_TRACING; case BPF_LSM_MAC: diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 5776d2b8e36e..ae7e4fdfe2a3 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -182,7 +182,8 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog) switch (ptype) { case BPF_PROG_TYPE_TRACING: if (eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT || - eatype == BPF_MODIFY_RETURN || eatype == BPF_TRACE_FSESSION) + eatype == BPF_MODIFY_RETURN || eatype == BPF_TRACE_FSESSION || + eatype == BPF_TRACE_FENTRY_MULTI || eatype == BPF_TRACE_FEXIT_MULTI) return true; return false; case BPF_PROG_TYPE_LSM: @@ -781,10 +782,12 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) { switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: + case BPF_TRACE_FENTRY_MULTI: return BPF_TRAMP_FENTRY; case BPF_MODIFY_RETURN: return BPF_TRAMP_MODIFY_RETURN; case BPF_TRACE_FEXIT: + case BPF_TRACE_FEXIT_MULTI: return BPF_TRAMP_FEXIT; case BPF_TRACE_FSESSION: return BPF_TRAMP_FSESSION; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 926ff63a0b61..0e593f3335e9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16382,6 +16382,8 @@ static bool return_retval_range(struct bpf_verifier_env *env, struct bpf_retval_ case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: + case BPF_TRACE_FENTRY_MULTI: + case BPF_TRACE_FEXIT_MULTI: *range = retval_range(0, 0); break; case BPF_TRACE_RAW_TP: @@ -18772,6 +18774,11 @@ static int check_attach_modify_return(unsigned long addr, const char *func_name) #endif /* CONFIG_FUNCTION_ERROR_INJECTION */ +static bool is_tracing_multi_id(const struct bpf_prog *prog, u32 btf_id) +{ + return is_tracing_multi(prog->expected_attach_type) && bpf_multi_func_btf_id[0] == btf_id; +} + int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *prog, const struct bpf_prog *tgt_prog, @@ -18894,6 +18901,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, prog_extension && (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY || tgt_prog->expected_attach_type == BPF_TRACE_FEXIT || + tgt_prog->expected_attach_type == BPF_TRACE_FENTRY_MULTI || + tgt_prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI || tgt_prog->expected_attach_type == BPF_TRACE_FSESSION)) { /* Program extensions can extend all program types * except fentry/fexit. The reason is the following. @@ -19000,6 +19009,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: + case BPF_TRACE_FENTRY_MULTI: + case BPF_TRACE_FEXIT_MULTI: if (prog->expected_attach_type == BPF_TRACE_FSESSION && !bpf_jit_supports_fsession()) { bpf_log(log, "JIT does not support fsession\n"); @@ -19029,7 +19040,18 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, if (ret < 0) return ret; - if (tgt_prog) { + /* + * *.multi programs don't need an address during program + * verification, we just take the module ref if needed. + */ + if (is_tracing_multi_id(prog, btf_id)) { + if (btf_is_module(btf)) { + mod = btf_try_get_module(btf); + if (!mod) + return -ENOENT; + } + addr = 0; + } else if (tgt_prog) { if (subprog == 0) addr = (long) tgt_prog->bpf_func; else @@ -19057,6 +19079,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: + /* *.multi sleepable programs will pass initial sleepable check, + * the actual attached btf ids are checked later during the link + * attachment. + */ + if (is_tracing_multi_id(prog, btf_id)) + ret = 0; if (!check_attach_sleepable(btf_id, addr, tname)) ret = 0; /* fentry/fexit/fmod_ret progs can also be sleepable if they are @@ -19167,6 +19195,8 @@ static bool can_be_sleepable(struct bpf_prog *prog) case BPF_TRACE_ITER: case BPF_TRACE_FSESSION: case BPF_TRACE_RAW_TP: + case BPF_TRACE_FENTRY_MULTI: + case BPF_TRACE_FEXIT_MULTI: return true; default: return false; @@ -19260,6 +19290,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return -EINVAL; } + /* + * We don't get trampoline for tracing_multi programs at this point, + * it's done when tracing_multi link is created. + */ + if (prog->type == BPF_PROG_TYPE_TRACING && + is_tracing_multi(prog->expected_attach_type)) + return 0; + key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); tr = bpf_trampoline_get(key, &tgt_info); if (!tr) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index c9aea7052ba7..67769c700cae 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -703,6 +703,8 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: + case BPF_TRACE_FENTRY_MULTI: + case BPF_TRACE_FEXIT_MULTI: if (bpf_fentry_test1(1) != 2 || bpf_fentry_test2(2, 3) != 5 || bpf_fentry_test3(4, 5, 6) != 15 || diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3829db087449..1b9aacf468e5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1156,6 +1156,8 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_SESSION, BPF_TRACE_UPROBE_SESSION, BPF_TRACE_FSESSION, + BPF_TRACE_FENTRY_MULTI, + BPF_TRACE_FEXIT_MULTI, __MAX_BPF_ATTACH_TYPE }; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 1354bcbc8b30..1b09381d16ff 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -136,6 +136,8 @@ static const char * const attach_type_name[] = { [BPF_NETKIT_PEER] = "netkit_peer", [BPF_TRACE_KPROBE_SESSION] = "trace_kprobe_session", [BPF_TRACE_UPROBE_SESSION] = "trace_uprobe_session", + [BPF_TRACE_FENTRY_MULTI] = "trace_fentry_multi", + [BPF_TRACE_FEXIT_MULTI] = "trace_fexit_multi", }; static const char * const link_type_name[] = { -- cgit v1.3-14-g43fede From c1d32dea5d4694c1a6c14d1d1c3192d0e18ffc7b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 6 Jun 2026 14:39:38 +0200 Subject: bpf: Add support for tracing multi link Adding new link to allow to attach program to multiple function BTF IDs. The link is represented by struct bpf_tracing_multi_link. To configure the link, new fields are added to bpf_attr::link_create to pass array of BTF IDs; struct { __aligned_u64 ids; __u32 cnt; } tracing_multi; Each BTF ID represents function (BTF_KIND_FUNC) that the link will attach bpf program to. We use previously added bpf_trampoline_multi_attach/detach functions to attach/detach the link. The linkinfo/fdinfo callbacks will be implemented in following changes. Note this is supported only for archs (x86_64) with ftrace direct and have single ops support. CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS && CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS Note using sort_r (instead of plain sort) in check_dup_ids, because we will use the swap callback in following changes. Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20260606123955.345967-14-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_types.h | 1 + include/linux/trace_events.h | 6 ++ include/uapi/linux/bpf.h | 5 ++ kernel/bpf/syscall.c | 2 + kernel/trace/bpf_trace.c | 130 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 6 ++ tools/lib/bpf/libbpf.c | 1 + 7 files changed, 151 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 56e4c3f983d3..e5906829aa6f 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -156,3 +156,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_UPROBE_MULTI, uprobe_multi) +BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING_MULTI, tracing_multi) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index d49338c44014..308c76b57d13 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -787,6 +787,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, unsigned long *missed); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -844,6 +845,11 @@ bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } +static inline int +bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} #endif enum { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 28d127e5040a..9f603731d267 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1182,6 +1182,7 @@ enum bpf_link_type { BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, BPF_LINK_TYPE_SOCKMAP = 14, + BPF_LINK_TYPE_TRACING_MULTI = 15, __MAX_BPF_LINK_TYPE, }; @@ -1877,6 +1878,10 @@ union bpf_attr { }; __u64 expected_revision; } cgroup; + struct { + __aligned_u64 ids; + __u32 cnt; + } tracing_multi; }; } link_create; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index efdd6639a598..d551b9da0cfb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5885,6 +5885,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = bpf_iter_link_attach(attr, uattr, prog); else if (prog->expected_attach_type == BPF_LSM_CGROUP) ret = cgroup_bpf_link_attach(attr, prog); + else if (is_tracing_multi(prog->expected_attach_type)) + ret = bpf_tracing_multi_attach(prog, attr); else ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d853f97bd154..9e3cb547651e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -42,6 +42,7 @@ #define MAX_UPROBE_MULTI_CNT (1U << 20) #define MAX_KPROBE_MULTI_CNT (1U << 20) +#define MAX_TRACING_MULTI_CNT (1U << 20) #ifdef CONFIG_MODULES struct bpf_trace_module { @@ -3641,3 +3642,132 @@ __bpf_kfunc int bpf_copy_from_user_task_str_dynptr(const struct bpf_dynptr *dptr } __bpf_kfunc_end_defs(); + +#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) && \ + defined(CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS) + +static void bpf_tracing_multi_link_release(struct bpf_link *link) +{ + struct bpf_tracing_multi_link *tr_link = + container_of(link, struct bpf_tracing_multi_link, link); + + WARN_ON_ONCE(bpf_trampoline_multi_detach(link->prog, tr_link)); +} + +static void bpf_tracing_multi_link_dealloc(struct bpf_link *link) +{ + struct bpf_tracing_multi_link *tr_link = + container_of(link, struct bpf_tracing_multi_link, link); + + kvfree(tr_link); +} + +static const struct bpf_link_ops bpf_tracing_multi_link_lops = { + .release = bpf_tracing_multi_link_release, + .dealloc_deferred = bpf_tracing_multi_link_dealloc, +}; + +static int ids_cmp_r(const void *pa, const void *pb, const void *priv __maybe_unused) +{ + u32 a = *(u32 *) pa; + u32 b = *(u32 *) pb; + + return (a > b) - (a < b); +} + +static void ids_swap_r(void *a, void *b, int size __maybe_unused, + const void *priv __maybe_unused) +{ + u32 *id_a = a, *id_b = b; + + swap(*id_a, *id_b); +} + +static int check_dup_ids(u32 *ids, u32 cnt) +{ + int err = 0; + + /* + * Sort ids array (together with cookies array if defined) + * and check it for duplicates. The ids and cookies arrays + * are left sorted. + */ + sort_r_nonatomic(ids, cnt, sizeof(ids[0]), ids_cmp_r, ids_swap_r, NULL); + + for (int i = 1; i < cnt; i++) { + if (ids[i] == ids[i - 1]) { + err = -EINVAL; + break; + } + } + return err; +} + +int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) +{ + struct bpf_tracing_multi_link *link = NULL; + struct bpf_link_primer link_primer; + u32 cnt, *ids = NULL; + u32 __user *uids; + int err; + + uids = u64_to_user_ptr(attr->link_create.tracing_multi.ids); + cnt = attr->link_create.tracing_multi.cnt; + + if (!cnt || !uids) + return -EINVAL; + if (cnt > MAX_TRACING_MULTI_CNT) + return -E2BIG; + if (attr->link_create.flags || attr->link_create.target_fd) + return -EINVAL; + + ids = kvmalloc_objs(*ids, cnt); + if (!ids) + return -ENOMEM; + + if (copy_from_user(ids, uids, cnt * sizeof(*ids))) { + err = -EFAULT; + goto error; + } + + err = check_dup_ids(ids, cnt); + if (err) + goto error; + + link = kvzalloc_flex(*link, nodes, cnt); + if (!link) { + err = -ENOMEM; + goto error; + } + + bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING_MULTI, + &bpf_tracing_multi_link_lops, prog, prog->expected_attach_type); + + err = bpf_link_prime(&link->link, &link_primer); + if (err) + goto error; + + link->nodes_cnt = cnt; + + err = bpf_trampoline_multi_attach(prog, ids, link); + kvfree(ids); + if (err) { + bpf_link_cleanup(&link_primer); + return err; + } + return bpf_link_settle(&link_primer); + +error: + kvfree(ids); + kvfree(link); + return err; +} + +#else + +int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} + +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS && CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1b9aacf468e5..9f603731d267 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1182,6 +1182,7 @@ enum bpf_link_type { BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, BPF_LINK_TYPE_SOCKMAP = 14, + BPF_LINK_TYPE_TRACING_MULTI = 15, __MAX_BPF_LINK_TYPE, }; @@ -1877,6 +1878,10 @@ union bpf_attr { }; __u64 expected_revision; } cgroup; + struct { + __aligned_u64 ids; + __u32 cnt; + } tracing_multi; }; } link_create; @@ -7254,6 +7259,7 @@ enum { TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */ + }; enum { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 1b09381d16ff..59405d318624 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -156,6 +156,7 @@ static const char * const link_type_name[] = { [BPF_LINK_TYPE_UPROBE_MULTI] = "uprobe_multi", [BPF_LINK_TYPE_NETKIT] = "netkit", [BPF_LINK_TYPE_SOCKMAP] = "sockmap", + [BPF_LINK_TYPE_TRACING_MULTI] = "tracing_multi", }; static const char * const map_type_name[] = { -- cgit v1.3-14-g43fede From 46b42af27d40021a97c147d23de8cb29eb5020df Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 6 Jun 2026 14:39:39 +0200 Subject: bpf: Add support for tracing_multi link cookies Add support to specify cookies for tracing_multi link. Cookies are provided in array where each value is paired with provided BTF ID value with the same array index. Such cookie can be retrieved by bpf program with bpf_get_attach_cookie helper call. We need to sort cookies array together with ids array in check_dup_ids, to keep the id->cookie relation. Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20260606123955.345967-15-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/trampoline.c | 1 + kernel/trace/bpf_trace.c | 37 +++++++++++++++++++++++++++++++++---- tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 37 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bcf70f810d2c..e9d2b42a3981 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1971,6 +1971,7 @@ struct bpf_tracing_multi_data { struct bpf_tracing_multi_link { struct bpf_link link; struct bpf_tracing_multi_data data; + u64 *cookies; int nodes_cnt; struct bpf_tracing_multi_node nodes[] __counted_by(nodes_cnt); }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9f603731d267..569c15e1cae3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1880,6 +1880,7 @@ union bpf_attr { } cgroup; struct { __aligned_u64 ids; + __aligned_u64 cookies; __u32 cnt; } tracing_multi; }; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 957e5d7f9554..a3537fda50cf 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -1613,6 +1613,7 @@ int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids, mnode->trampoline = tr; mnode->node.link = &link->link; + mnode->node.cookie = link->cookies ? link->cookies[i] : 0; cond_resched(); } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 9e3cb547651e..e33492739ed1 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3659,6 +3659,7 @@ static void bpf_tracing_multi_link_dealloc(struct bpf_link *link) struct bpf_tracing_multi_link *tr_link = container_of(link, struct bpf_tracing_multi_link, link); + kvfree(tr_link->cookies); kvfree(tr_link); } @@ -3678,13 +3679,24 @@ static int ids_cmp_r(const void *pa, const void *pb, const void *priv __maybe_un static void ids_swap_r(void *a, void *b, int size __maybe_unused, const void *priv __maybe_unused) { - u32 *id_a = a, *id_b = b; + u64 *cookie_a, *cookie_b, *cookies; + u32 *id_a = a, *id_b = b, *ids; + void **data = (void **) priv; + ids = data[0]; + cookies = data[1]; + + if (cookies) { + cookie_a = cookies + (id_a - ids); + cookie_b = cookies + (id_b - ids); + swap(*cookie_a, *cookie_b); + } swap(*id_a, *id_b); } -static int check_dup_ids(u32 *ids, u32 cnt) +static int check_dup_ids(u32 *ids, u64 *cookies, u32 cnt) { + void *data[2] = { ids, cookies }; int err = 0; /* @@ -3692,7 +3704,7 @@ static int check_dup_ids(u32 *ids, u32 cnt) * and check it for duplicates. The ids and cookies arrays * are left sorted. */ - sort_r_nonatomic(ids, cnt, sizeof(ids[0]), ids_cmp_r, ids_swap_r, NULL); + sort_r_nonatomic(ids, cnt, sizeof(ids[0]), ids_cmp_r, ids_swap_r, data); for (int i = 1; i < cnt; i++) { if (ids[i] == ids[i - 1]) { @@ -3708,6 +3720,8 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) struct bpf_tracing_multi_link *link = NULL; struct bpf_link_primer link_primer; u32 cnt, *ids = NULL; + u64 __user *ucookies; + u64 *cookies = NULL; u32 __user *uids; int err; @@ -3730,7 +3744,20 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) goto error; } - err = check_dup_ids(ids, cnt); + ucookies = u64_to_user_ptr(attr->link_create.tracing_multi.cookies); + if (ucookies) { + cookies = kvmalloc_objs(*cookies, cnt); + if (!cookies) { + err = -ENOMEM; + goto error; + } + if (copy_from_user(cookies, ucookies, cnt * sizeof(*cookies))) { + err = -EFAULT; + goto error; + } + } + + err = check_dup_ids(ids, cookies, cnt); if (err) goto error; @@ -3748,6 +3775,7 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) goto error; link->nodes_cnt = cnt; + link->cookies = cookies; err = bpf_trampoline_multi_attach(prog, ids, link); kvfree(ids); @@ -3758,6 +3786,7 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) return bpf_link_settle(&link_primer); error: + kvfree(cookies); kvfree(ids); kvfree(link); return err; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9f603731d267..569c15e1cae3 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1880,6 +1880,7 @@ union bpf_attr { } cgroup; struct { __aligned_u64 ids; + __aligned_u64 cookies; __u32 cnt; } tracing_multi; }; -- cgit v1.3-14-g43fede From ba042ed6446fc524c1d804227765b45616f9cba3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 6 Jun 2026 14:39:40 +0200 Subject: bpf: Add support for tracing_multi link session Adding support to use session attachment with tracing_multi link. Adding new BPF_TRACE_FSESSION_MULTI program attach type, that follows the BPF_TRACE_FSESSION behaviour but on the tracing_multi link. Such program is called on entry and exit of the attached function and allows to pass cookie value from entry to exit execution. Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20260606123955.345967-16-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 +++++- include/uapi/linux/bpf.h | 1 + kernel/bpf/fixups.c | 1 + kernel/bpf/syscall.c | 1 + kernel/bpf/trampoline.c | 44 ++++++++++++++++++++++++++++++++++-------- kernel/bpf/verifier.c | 20 ++++++++++++++----- kernel/trace/bpf_trace.c | 15 +++++++++++++- net/bpf/test_run.c | 1 + tools/include/uapi/linux/bpf.h | 1 + tools/lib/bpf/libbpf.c | 1 + 10 files changed, 76 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e9d2b42a3981..62bba7a4876f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1972,6 +1972,7 @@ struct bpf_tracing_multi_link { struct bpf_link link; struct bpf_tracing_multi_data data; u64 *cookies; + struct bpf_tramp_node *fexits; int nodes_cnt; struct bpf_tracing_multi_node nodes[] __counted_by(nodes_cnt); }; @@ -2159,7 +2160,8 @@ static inline void bpf_prog_put_recursion_context(struct bpf_prog *prog) static inline bool is_tracing_multi(enum bpf_attach_type type) { - return type == BPF_TRACE_FENTRY_MULTI || type == BPF_TRACE_FEXIT_MULTI; + return type == BPF_TRACE_FENTRY_MULTI || type == BPF_TRACE_FEXIT_MULTI || + type == BPF_TRACE_FSESSION_MULTI; } #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) @@ -2286,6 +2288,8 @@ static inline int bpf_fsession_cnt(struct bpf_tramp_nodes *nodes) for (int i = 0; i < nodes[BPF_TRAMP_FENTRY].nr_nodes; i++) { if (fentries.nodes[i]->link->prog->expected_attach_type == BPF_TRACE_FSESSION) cnt++; + if (fentries.nodes[i]->link->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) + cnt++; } return cnt; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 569c15e1cae3..11dd610fa5fa 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1158,6 +1158,7 @@ enum bpf_attach_type { BPF_TRACE_FSESSION, BPF_TRACE_FENTRY_MULTI, BPF_TRACE_FEXIT_MULTI, + BPF_TRACE_FSESSION_MULTI, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c index 0cf9735929f5..3cf2cc6e3ab6 100644 --- a/kernel/bpf/fixups.c +++ b/kernel/bpf/fixups.c @@ -2187,6 +2187,7 @@ patch_map_ops_generic: if (eatype == BPF_TRACE_FEXIT || eatype == BPF_TRACE_FSESSION || eatype == BPF_TRACE_FEXIT_MULTI || + eatype == BPF_TRACE_FSESSION_MULTI || eatype == BPF_MODIFY_RETURN) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d551b9da0cfb..d4188a992bd8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4498,6 +4498,7 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: + case BPF_TRACE_FSESSION_MULTI: case BPF_TRACE_FENTRY_MULTI: case BPF_TRACE_FEXIT_MULTI: case BPF_MODIFY_RETURN: diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index a3537fda50cf..1a721fc4bef5 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -183,7 +183,8 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog) case BPF_PROG_TYPE_TRACING: if (eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT || eatype == BPF_MODIFY_RETURN || eatype == BPF_TRACE_FSESSION || - eatype == BPF_TRACE_FENTRY_MULTI || eatype == BPF_TRACE_FEXIT_MULTI) + eatype == BPF_TRACE_FENTRY_MULTI || eatype == BPF_TRACE_FEXIT_MULTI || + eatype == BPF_TRACE_FSESSION_MULTI) return true; return false; case BPF_PROG_TYPE_LSM: @@ -790,6 +791,7 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) case BPF_TRACE_FEXIT_MULTI: return BPF_TRAMP_FEXIT; case BPF_TRACE_FSESSION: + case BPF_TRACE_FSESSION_MULTI: return BPF_TRAMP_FSESSION; case BPF_LSM_MAC: if (!prog->aux->attach_func_proto->type) @@ -822,13 +824,30 @@ static int bpf_freplace_check_tgt_prog(struct bpf_prog *tgt_prog) return 0; } +static struct bpf_tramp_node *fsession_exit(struct bpf_tramp_node *node) +{ + if (node->link->type == BPF_LINK_TYPE_TRACING) { + struct bpf_tracing_link *link; + + link = container_of(node->link, struct bpf_tracing_link, link.link); + return &link->fexit; + } else if (node->link->type == BPF_LINK_TYPE_TRACING_MULTI) { + struct bpf_tracing_multi_link *link; + struct bpf_tracing_multi_node *mnode; + + link = container_of(node->link, struct bpf_tracing_multi_link, link); + mnode = container_of(node, struct bpf_tracing_multi_node, node); + return &link->fexits[mnode - link->nodes]; + } + return NULL; +} + static int bpf_trampoline_add_prog(struct bpf_trampoline *tr, struct bpf_tramp_node *node, int cnt) { - struct bpf_tracing_link *tr_link = NULL; enum bpf_tramp_prog_type kind; - struct bpf_tramp_node *node_existing; + struct bpf_tramp_node *node_existing, *fexit; struct hlist_head *prog_list; kind = bpf_attach_type_to_tramp(node->link->prog); @@ -853,8 +872,10 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr, hlist_add_head(&node->tramp_hlist, prog_list); if (kind == BPF_TRAMP_FSESSION) { tr->progs_cnt[BPF_TRAMP_FENTRY]++; - tr_link = container_of(node, struct bpf_tracing_link, link.node); - hlist_add_head(&tr_link->fexit.tramp_hlist, &tr->progs_hlist[BPF_TRAMP_FEXIT]); + fexit = fsession_exit(node); + if (WARN_ON_ONCE(!fexit)) + return -EINVAL; + hlist_add_head(&fexit->tramp_hlist, &tr->progs_hlist[BPF_TRAMP_FEXIT]); tr->progs_cnt[BPF_TRAMP_FEXIT]++; } else { tr->progs_cnt[kind]++; @@ -865,13 +886,15 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr, static void bpf_trampoline_remove_prog(struct bpf_trampoline *tr, struct bpf_tramp_node *node) { - struct bpf_tracing_link *tr_link; enum bpf_tramp_prog_type kind; + struct bpf_tramp_node *fexit; kind = bpf_attach_type_to_tramp(node->link->prog); if (kind == BPF_TRAMP_FSESSION) { - tr_link = container_of(node, struct bpf_tracing_link, link.node); - hlist_del_init(&tr_link->fexit.tramp_hlist); + fexit = fsession_exit(node); + if (WARN_ON_ONCE(!fexit)) + return; + hlist_del_init(&fexit->tramp_hlist); tr->progs_cnt[BPF_TRAMP_FEXIT]--; kind = BPF_TRAMP_FENTRY; } @@ -1615,6 +1638,11 @@ int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids, mnode->node.link = &link->link; mnode->node.cookie = link->cookies ? link->cookies[i] : 0; + if (prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) { + link->fexits[i].link = &link->link; + link->fexits[i].cookie = link->cookies ? link->cookies[i] : 0; + } + cond_resched(); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5c594047ff0a..0c1cf506c219 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16384,6 +16384,7 @@ static bool return_retval_range(struct bpf_verifier_env *env, struct bpf_retval_ case BPF_TRACE_FSESSION: case BPF_TRACE_FENTRY_MULTI: case BPF_TRACE_FEXIT_MULTI: + case BPF_TRACE_FSESSION_MULTI: *range = retval_range(0, 0); break; case BPF_TRACE_RAW_TP: @@ -18952,7 +18953,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, tgt_prog->expected_attach_type == BPF_TRACE_FEXIT || tgt_prog->expected_attach_type == BPF_TRACE_FENTRY_MULTI || tgt_prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI || - tgt_prog->expected_attach_type == BPF_TRACE_FSESSION)) { + tgt_prog->expected_attach_type == BPF_TRACE_FSESSION || + tgt_prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) { /* Program extensions can extend all program types * except fentry/fexit. The reason is the following. * The fentry/fexit programs are used for performance @@ -19058,9 +19060,11 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: + case BPF_TRACE_FSESSION_MULTI: case BPF_TRACE_FENTRY_MULTI: case BPF_TRACE_FEXIT_MULTI: - if (prog->expected_attach_type == BPF_TRACE_FSESSION && + if ((prog->expected_attach_type == BPF_TRACE_FSESSION || + prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) && !bpf_jit_supports_fsession()) { bpf_log(log, "JIT does not support fsession\n"); return -EOPNOTSUPP; @@ -19215,6 +19219,7 @@ static bool can_be_sleepable(struct bpf_prog *prog) case BPF_TRACE_RAW_TP: case BPF_TRACE_FENTRY_MULTI: case BPF_TRACE_FEXIT_MULTI: + case BPF_TRACE_FSESSION_MULTI: return true; default: return false; @@ -19301,6 +19306,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return -EINVAL; } else if ((prog->expected_attach_type == BPF_TRACE_FEXIT || prog->expected_attach_type == BPF_TRACE_FSESSION || + prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI || prog->expected_attach_type == BPF_MODIFY_RETURN) && btf_id_set_contains(&noreturn_deny, btf_id)) { verbose(env, "Attaching fexit/fsession/fmod_ret to __noreturn function '%s' is rejected.\n", @@ -19340,7 +19346,8 @@ int bpf_check_attach_btf_id_multi(struct btf *btf, struct bpf_prog *prog, u32 bt return -EINVAL; /* Check noreturn attachment. */ - if (prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI && + if ((prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI || + prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) && btf_id_set_contains(&noreturn_deny, btf_id)) return -EINVAL; /* Check denied attachment. */ @@ -19623,7 +19630,9 @@ int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); *cnt = 1; } else if (desc->func_id == special_kfunc_list[KF_bpf_session_is_return] && - env->prog->expected_attach_type == BPF_TRACE_FSESSION) { + (env->prog->expected_attach_type == BPF_TRACE_FSESSION || + env->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) { + /* * inline the bpf_session_is_return() for fsession: * bool bpf_session_is_return(void *ctx) @@ -19636,7 +19645,8 @@ int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1); *cnt = 3; } else if (desc->func_id == special_kfunc_list[KF_bpf_session_cookie] && - env->prog->expected_attach_type == BPF_TRACE_FSESSION) { + (env->prog->expected_attach_type == BPF_TRACE_FSESSION || + env->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) { /* * inline bpf_session_cookie() for fsession: * __u64 *bpf_session_cookie(void *ctx) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e33492739ed1..a0d688fffc5a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1334,7 +1334,8 @@ static inline bool is_uprobe_session(const struct bpf_prog *prog) static inline bool is_trace_fsession(const struct bpf_prog *prog) { return prog->type == BPF_PROG_TYPE_TRACING && - prog->expected_attach_type == BPF_TRACE_FSESSION; + (prog->expected_attach_type == BPF_TRACE_FSESSION || + prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI); } static const struct bpf_func_proto * @@ -3659,6 +3660,7 @@ static void bpf_tracing_multi_link_dealloc(struct bpf_link *link) struct bpf_tracing_multi_link *tr_link = container_of(link, struct bpf_tracing_multi_link, link); + kvfree(tr_link->fexits); kvfree(tr_link->cookies); kvfree(tr_link); } @@ -3718,6 +3720,7 @@ static int check_dup_ids(u32 *ids, u64 *cookies, u32 cnt) int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) { struct bpf_tracing_multi_link *link = NULL; + struct bpf_tramp_node *fexits = NULL; struct bpf_link_primer link_primer; u32 cnt, *ids = NULL; u64 __user *ucookies; @@ -3761,6 +3764,14 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) if (err) goto error; + if (prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) { + fexits = kvmalloc_objs(*fexits, cnt); + if (!fexits) { + err = -ENOMEM; + goto error; + } + } + link = kvzalloc_flex(*link, nodes, cnt); if (!link) { err = -ENOMEM; @@ -3776,6 +3787,7 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) link->nodes_cnt = cnt; link->cookies = cookies; + link->fexits = fexits; err = bpf_trampoline_multi_attach(prog, ids, link); kvfree(ids); @@ -3786,6 +3798,7 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) return bpf_link_settle(&link_primer); error: + kvfree(fexits); kvfree(cookies); kvfree(ids); kvfree(link); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 67769c700cae..a831682ee982 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -705,6 +705,7 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, case BPF_TRACE_FSESSION: case BPF_TRACE_FENTRY_MULTI: case BPF_TRACE_FEXIT_MULTI: + case BPF_TRACE_FSESSION_MULTI: if (bpf_fentry_test1(1) != 2 || bpf_fentry_test2(2, 3) != 5 || bpf_fentry_test3(4, 5, 6) != 15 || diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 569c15e1cae3..11dd610fa5fa 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1158,6 +1158,7 @@ enum bpf_attach_type { BPF_TRACE_FSESSION, BPF_TRACE_FENTRY_MULTI, BPF_TRACE_FEXIT_MULTI, + BPF_TRACE_FSESSION_MULTI, __MAX_BPF_ATTACH_TYPE }; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 59405d318624..62f088359c5e 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -138,6 +138,7 @@ static const char * const attach_type_name[] = { [BPF_TRACE_UPROBE_SESSION] = "trace_uprobe_session", [BPF_TRACE_FENTRY_MULTI] = "trace_fentry_multi", [BPF_TRACE_FEXIT_MULTI] = "trace_fexit_multi", + [BPF_TRACE_FSESSION_MULTI] = "trace_fsession_multi", }; static const char * const link_type_name[] = { -- cgit v1.3-14-g43fede From c6153ed23ed6a2bb8a5891382c06134674610f86 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Thu, 16 Apr 2026 19:01:18 +0100 Subject: btrfs: add ioctl GET_CSUMS to read raw checksums from file range Add a new unprivileged BTRFS_IOC_GET_CSUMS ioctl, which can be used to query the on-disk csums for a file range. The ioctl is deliberately per-file rather than exposing raw csum tree lookups, to avoid leaking information to users about files they may not have access to. This is done by userspace passing a struct btrfs_ioctl_get_csums_args to the kernel, which details the offset and length we're interested in, and a buffer for the kernel to write its results into. The kernel writes a struct btrfs_ioctl_get_csums_entry into the buffer, followed by the csums if available. The maximum size of the user buffer is capped to 16MiB. If the extent is an uncompressed, non-NODATASUM extent, the kernel sets the entry type to BTRFS_GET_CSUMS_HAS_CSUMS and follows it with the csums. If it is sparse, preallocated, or beyond the EOF, it sets the type to BTRFS_GET_CSUMS_ZEROED - this is so userspace knows it can use the precomputed hash of the zero sector. Otherwise, it sets the type to BTRFS_GET_CSUMS_NODATASUM, BTRFS_GET_CSUMS_COMPRESSED, BTRFS_GET_CSUM_ENCRYPTED, or BTRFS_GET_CSUM_INLINE. For example, a file with a [0, 4K) hole and [4K, 12K) data extent would produce the following output buffer: | [0, 4K) ZEROED | [4K, 12K) HAS_CSUMS | csum data | We do store the csums of compressed extents, but we deliberately don't return them here: they're calculated over the compressed data, not the uncompressed data that's returned to userspace. Similarly for encrypted data, once encryption is supported, in which the csums will be on the ciphertext. The main use case for this is for speeding up mkfs.btrfs --rootdir. For the case when the source FS is btrfs and using the same csum algorithm, we can avoid having to recalculate the csums - in my synthetic benchmarks (16GB file on a spinning-rust drive), this resulted in a ~11% speed-up (218s to 196s). When using the --reflink option added in btrfs-progs v6.16.1, we can forgo reading the data entirely, resulting a ~2200% speed-up on the same test (128s to 6s). # mkdir rootdir # dd if=/dev/urandom of=rootdir/file bs=4096 count=4194304 (without ioctl) # echo 3 > /proc/sys/vm/drop_caches # time mkfs.btrfs --rootdir rootdir testimg ... real 3m37.965s user 0m5.496s sys 0m6.125s # echo 3 > /proc/sys/vm/drop_caches # time mkfs.btrfs --rootdir rootdir --reflink testimg ... real 2m8.342s user 0m5.472s sys 0m1.667s (with ioctl) # echo 3 > /proc/sys/vm/drop_caches # time mkfs.btrfs --rootdir rootdir testimg ... real 3m15.865s user 0m4.258s sys 0m6.261s # echo 3 > /proc/sys/vm/drop_caches # time mkfs.btrfs --rootdir rootdir --reflink testimg ... real 0m5.847s user 0m2.899s sys 0m0.097s Another notable use case is for deduplication, where reading the checksums may serve as a hint instead of reading the whole file data. Reviewed-by: Qu Wenruo Signed-off-by: Mark Harmstone Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 339 +++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/btrfs.h | 34 +++++ 2 files changed, 373 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e60b13b27a6d..6e99e5f8d32c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -56,6 +56,7 @@ #include "uuid-tree.h" #include "ioctl.h" #include "file.h" +#include "file-item.h" #include "scrub.h" #include "super.h" @@ -5060,6 +5061,342 @@ static int btrfs_ioctl_shutdown(struct btrfs_fs_info *fs_info, unsigned long arg return ret; } +#define GET_CSUMS_BUF_MAX SZ_16M + +static int copy_csums_to_user(struct btrfs_fs_info *fs_info, u64 disk_bytenr, + u64 len, u8 __user *buf) +{ + struct btrfs_root *csum_root; + struct btrfs_ordered_sum *sums; + LIST_HEAD(list); + const u32 csum_size = fs_info->csum_size; + int ret; + + csum_root = btrfs_csum_root(fs_info, disk_bytenr); + if (unlikely(!csum_root)) { + btrfs_err(fs_info, "missing csum root for extent at bytenr %llu", disk_bytenr); + return -EUCLEAN; + } + + ret = btrfs_lookup_csums_list(csum_root, disk_bytenr, + disk_bytenr + len - 1, &list, false); + if (ret < 0) + return ret; + + ret = 0; + while (!list_empty(&list)) { + u64 offset; + size_t copy_size; + + sums = list_first_entry(&list, struct btrfs_ordered_sum, list); + list_del(&sums->list); + + offset = ((sums->logical - disk_bytenr) >> fs_info->sectorsize_bits) * csum_size; + copy_size = (sums->len >> fs_info->sectorsize_bits) * csum_size; + + if (copy_to_user(buf + offset, sums->sums, copy_size)) { + kfree(sums); + ret = -EFAULT; + goto out; + } + + kfree(sums); + } + +out: + while (!list_empty(&list)) { + sums = list_first_entry(&list, struct btrfs_ordered_sum, list); + list_del(&sums->list); + kfree(sums); + } + return ret; +} + +static int btrfs_ioctl_get_csums(struct file *file, void __user *argp) +{ + struct inode *vfs_inode = file_inode(file); + struct btrfs_inode *inode = BTRFS_I(vfs_inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_root *root = inode->root; + struct btrfs_ioctl_get_csums_args args; + BTRFS_PATH_AUTO_FREE(path); + const u64 ino = btrfs_ino(inode); + const u32 csum_size = fs_info->csum_size; + u8 __user *ubuf; + u64 buf_limit; + u64 buf_used = 0; + u64 cur_offset; + u64 end_offset; + u64 prev_extent_end; + struct btrfs_key key; + int ret; + + if (!(file->f_mode & FMODE_READ)) + return -EBADF; + + if (!S_ISREG(vfs_inode->i_mode)) + return -EINVAL; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + if (!IS_ALIGNED(args.offset, fs_info->sectorsize) || + !IS_ALIGNED(args.length, fs_info->sectorsize)) + return -EINVAL; + if (args.length == 0) + return -EINVAL; + if (args.offset + args.length < args.offset) + return -EOVERFLOW; + if (args.flags != 0) + return -EINVAL; + if (args.buf_size < sizeof(struct btrfs_ioctl_get_csums_entry)) + return -EINVAL; + + buf_limit = min_t(u64, args.buf_size, GET_CSUMS_BUF_MAX); + ubuf = (u8 __user *)(argp + offsetof(struct btrfs_ioctl_get_csums_args, buf)); + + if (clear_user(ubuf, buf_limit)) + return -EFAULT; + + cur_offset = args.offset; + end_offset = args.offset + args.length; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = btrfs_wait_ordered_range(inode, cur_offset, args.length); + if (ret) + return ret; + + ret = down_read_interruptible(&vfs_inode->i_rwsem); + if (ret) + return ret; + + ret = btrfs_wait_ordered_range(inode, cur_offset, args.length); + if (ret) + goto out_unlock; + + /* NODATASUM early exit. */ + if (inode->flags & BTRFS_INODE_NODATASUM) { + struct btrfs_ioctl_get_csums_entry entry = { + .offset = cur_offset, + .length = end_offset - cur_offset, + .type = BTRFS_GET_CSUMS_NODATASUM, + }; + + if (copy_to_user(ubuf, &entry, sizeof(entry))) { + ret = -EFAULT; + goto out_unlock; + } + + buf_used = sizeof(entry); + cur_offset = end_offset; + goto done; + } + + prev_extent_end = cur_offset; + + while (cur_offset < end_offset) { + struct btrfs_file_extent_item *ei; + struct extent_buffer *leaf; + struct btrfs_ioctl_get_csums_entry entry = { 0 }; + u64 extent_end; + u64 disk_bytenr = 0; + u64 extent_offset = 0; + u64 range_start, range_len; + u64 entry_csum_size; + u64 key_offset; + int extent_type; + u8 compression; + u8 encryption; + + /* Search for the extent at or before cur_offset. */ + key.objectid = ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = cur_offset; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out_unlock; + + if (ret > 0 && path->slots[0] > 0) { + btrfs_item_key_to_cpu(path->nodes[0], &key, + path->slots[0] - 1); + if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY) { + path->slots[0]--; + if (btrfs_file_extent_end(path) <= cur_offset) + path->slots[0]++; + } + } + + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto out_unlock; + if (ret > 0) { + ret = 0; + btrfs_release_path(path); + break; + } + } + + leaf = path->nodes[0]; + + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); + if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) { + btrfs_release_path(path); + break; + } + + extent_end = btrfs_file_extent_end(path); + key_offset = key.offset; + + /* Read extent fields before releasing the path. */ + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + extent_type = btrfs_file_extent_type(leaf, ei); + compression = btrfs_file_extent_compression(leaf, ei); + encryption = btrfs_file_extent_encryption(leaf, ei); + + if (extent_type != BTRFS_FILE_EXTENT_INLINE) { + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr && compression == BTRFS_COMPRESS_NONE) + extent_offset = btrfs_file_extent_offset(leaf, ei); + } + + btrfs_release_path(path); + + /* Implicit hole (NO_HOLES feature). */ + if (prev_extent_end < key_offset) { + u64 hole_end = min(key_offset, end_offset); + u64 hole_len = hole_end - prev_extent_end; + + if (prev_extent_end >= cur_offset) { + entry.offset = prev_extent_end; + entry.length = hole_len; + entry.type = BTRFS_GET_CSUMS_ZEROED; + + if (buf_used + sizeof(entry) > buf_limit) + goto done; + if (copy_to_user(ubuf + buf_used, &entry, sizeof(entry))) { + ret = -EFAULT; + goto out_unlock; + } + buf_used += sizeof(entry); + cur_offset = hole_end; + } + + if (key_offset >= end_offset) { + cur_offset = end_offset; + break; + } + } + + /* Clamp to our query range. */ + range_start = max(cur_offset, key_offset); + range_len = min(extent_end, end_offset) - range_start; + + entry.offset = range_start; + entry.length = range_len; + + if (extent_type == BTRFS_FILE_EXTENT_INLINE) { + entry.type = BTRFS_GET_CSUMS_INLINE; + if (compression != BTRFS_COMPRESS_NONE) + entry.type |= BTRFS_GET_CSUMS_COMPRESSED; + if (encryption != 0) + entry.type |= BTRFS_GET_CSUMS_ENCRYPTED; + entry_csum_size = 0; + } else if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) { + entry.type = BTRFS_GET_CSUMS_ZEROED; + entry_csum_size = 0; + } else { + /* BTRFS_FILE_EXTENT_REG */ + if (disk_bytenr == 0) { + /* Explicit hole. */ + entry.type = BTRFS_GET_CSUMS_ZEROED; + entry_csum_size = 0; + } else if (encryption != 0 || compression != BTRFS_COMPRESS_NONE) { + entry.type = 0; + if (encryption != 0) + entry.type |= BTRFS_GET_CSUMS_ENCRYPTED; + if (compression != BTRFS_COMPRESS_NONE) + entry.type |= BTRFS_GET_CSUMS_COMPRESSED; + entry_csum_size = 0; + } else { + entry.type = BTRFS_GET_CSUMS_HAS_CSUMS; + entry_csum_size = (range_len >> fs_info->sectorsize_bits) * csum_size; + } + } + + /* Check if this entry (+ csum data) fits in the buffer. */ + if (buf_used + sizeof(entry) + entry_csum_size > buf_limit) { + if (buf_used == 0) { + ret = -EOVERFLOW; + goto out_unlock; + } + goto done; + } + + if (copy_to_user(ubuf + buf_used, &entry, sizeof(entry))) { + ret = -EFAULT; + goto out_unlock; + } + buf_used += sizeof(entry); + + if (entry.type == BTRFS_GET_CSUMS_HAS_CSUMS) { + ret = copy_csums_to_user(fs_info, + disk_bytenr + extent_offset + (range_start - key_offset), + range_len, ubuf + buf_used); + if (ret) + goto out_unlock; + buf_used += entry_csum_size; + } + + cur_offset = range_start + range_len; + prev_extent_end = extent_end; + + if (fatal_signal_pending(current)) { + if (buf_used == 0) { + ret = -EINTR; + goto out_unlock; + } + goto done; + } + + cond_resched(); + } + + /* Handle trailing implicit hole. */ + if (cur_offset < end_offset) { + struct btrfs_ioctl_get_csums_entry entry = { + .offset = prev_extent_end, + .length = end_offset - prev_extent_end, + .type = BTRFS_GET_CSUMS_ZEROED, + }; + + if (buf_used + sizeof(entry) <= buf_limit) { + if (copy_to_user(ubuf + buf_used, &entry, sizeof(entry))) { + ret = -EFAULT; + goto out_unlock; + } + buf_used += sizeof(entry); + cur_offset = end_offset; + } + } + +done: + args.offset = cur_offset; + args.length = (cur_offset < end_offset) ? end_offset - cur_offset : 0; + args.buf_size = buf_used; + + if (copy_to_user(argp, &args, sizeof(args))) + ret = -EFAULT; + +out_unlock: + up_read(&vfs_inode->i_rwsem); + return ret; +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -5217,6 +5554,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_subvol_sync(fs_info, argp); case BTRFS_IOC_SHUTDOWN: return btrfs_ioctl_shutdown(fs_info, arg); + case BTRFS_IOC_GET_CSUMS: + return btrfs_ioctl_get_csums(file, argp); } return -ENOTTY; diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 9165154a274d..9b576603b3f1 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -1100,6 +1100,38 @@ enum btrfs_err_code { BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET, }; +/* Flags for struct btrfs_ioctl_get_csums_entry::type. */ +#define BTRFS_GET_CSUMS_HAS_CSUMS (1U << 0) +#define BTRFS_GET_CSUMS_ZEROED (1U << 1) +#define BTRFS_GET_CSUMS_NODATASUM (1U << 2) +#define BTRFS_GET_CSUMS_COMPRESSED (1U << 3) +#define BTRFS_GET_CSUMS_ENCRYPTED (1U << 4) +#define BTRFS_GET_CSUMS_INLINE (1U << 5) + +struct btrfs_ioctl_get_csums_entry { + /* File offset of this range. */ + __u64 offset; + /* Length in bytes. */ + __u64 length; + /* One of BTRFS_GET_CSUMS_* types. */ + __u32 type; + /* Padding, must be 0. */ + __u32 reserved; +}; + +struct btrfs_ioctl_get_csums_args { + /* In/out: file offset in bytes. */ + __u64 offset; + /* In/out: range length in bytes. */ + __u64 length; + /* In/out: buffer capacity / bytes written. */ + __u64 buf_size; + /* In: flags, must be 0 for now. */ + __u64 flags; + /* Out: entries of type btrfs_ioctl_get_csums_entry + csum data */ + __u8 buf[]; +}; + /* Flags for IOC_SHUTDOWN, must match XFS_FSOP_GOING_FLAGS_* flags. */ #define BTRFS_SHUTDOWN_FLAGS_DEFAULT 0x0 #define BTRFS_SHUTDOWN_FLAGS_LOGFLUSH 0x1 @@ -1226,6 +1258,8 @@ enum btrfs_err_code { struct btrfs_ioctl_encoded_io_args) #define BTRFS_IOC_SUBVOL_SYNC_WAIT _IOW(BTRFS_IOCTL_MAGIC, 65, \ struct btrfs_ioctl_subvol_wait) +#define BTRFS_IOC_GET_CSUMS _IOWR(BTRFS_IOCTL_MAGIC, 66, \ + struct btrfs_ioctl_get_csums_args) /* Shutdown ioctl should follow XFS's interfaces, thus not using btrfs magic. */ #define BTRFS_IOC_SHUTDOWN _IOR('X', 125, __u32) -- cgit v1.3-14-g43fede From 38ecabc9af8be21fcb07f19634b56b6ec2d70268 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 29 May 2026 14:20:22 -0700 Subject: watchdog: uapi: add comments for what bit masks apply to Add comments similar to those in include/linux/watchdog.h so that the reader/user doesn't have to dig into the API documentation files for this. Signed-off-by: Randy Dunlap Signed-off-by: Guenter Roeck --- include/uapi/linux/watchdog.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/watchdog.h b/include/uapi/linux/watchdog.h index b15cde5c9054..fc73c17ee182 100644 --- a/include/uapi/linux/watchdog.h +++ b/include/uapi/linux/watchdog.h @@ -36,6 +36,7 @@ struct watchdog_info { #define WDIOF_UNKNOWN -1 /* Unknown flag error */ #define WDIOS_UNKNOWN -1 /* Unknown status error */ +/* Bit masks for watchdog_info.options, GETSTATUS and GETBOOTSTATUS ioctls */ #define WDIOF_OVERHEAT 0x0001 /* Reset due to CPU overheat */ #define WDIOF_FANFAULT 0x0002 /* Fan failed */ #define WDIOF_EXTERN1 0x0004 /* External relay 1 */ @@ -50,6 +51,7 @@ struct watchdog_info { other external alarm not a reboot */ #define WDIOF_KEEPALIVEPING 0x8000 /* Keep alive ping reply */ +/* Bit masks for WDIOC_SETOPTIONS ioctl */ #define WDIOS_DISABLECARD 0x0001 /* Turn off the watchdog timer */ #define WDIOS_ENABLECARD 0x0002 /* Turn on the watchdog timer */ #define WDIOS_TEMPPANIC 0x0004 /* Kernel panic on temperature trip */ -- cgit v1.3-14-g43fede From 69710a37bad62afc3d2f1fbf7b108e5f8b3808cd Mon Sep 17 00:00:00 2001 From: David 'equinox' Lamparter Date: Fri, 5 Jun 2026 18:41:44 +0200 Subject: if_ether.h: add 802.1AC, warn about GRE 0x00FE Because LLC wasn't complicated/annoying enough, there's 2 more "ethertypes" being used for it: - 0x8870 is pretty "normal", it got standardized in 802.1AC-2016/Cor1-2018 for transporting LLC frames > 1500 bytes. It simply replaces the length value (which is no longer encoded, and must now be derived from the packet.) The actual value dates back to 2001; https://datatracker.ietf.org/doc/html/draft-ietf-isis-ext-eth-01 (it was used without "proper" standardization for a long time) - 0x00fe is a doozy - actually "invalid" depending on how you look at it; it's used in GRE (and possibly GENEVE) tunnels to transport the IS-IS routing protocol. https://seclists.org/tcpdump/2002/q4/61 is the best/oldest source I could find. It's inspired by the 0xfe SAP value, a GRE packet with protocol 0x00fe is followed by a payload "as if" it was Ethernet with " 0xfe 0xfe 0x03". (Again the length isn't encoded explicitly anymore.) The 0x00fe value is quite close to other values the kernel is using internally for various things (after all they "won't clash for 1500 types"). Except this one does clash, and if someone unknowingly starts using it for something internal... we end up in a world of pain in getting IS-IS running on GRE tunnels. Hence the "WARNING". Signed-off-by: David 'equinox' Lamparter Cc: Andrew Lunn Link: https://patch.msgid.link/20260605164144.81184-1-equinox@diac24.net Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index fb5efc8e06cc..1ffac52c39df 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -82,6 +82,7 @@ #define ETH_P_PPP_DISC 0x8863 /* PPPoE discovery messages */ #define ETH_P_PPP_SES 0x8864 /* PPPoE session messages */ #define ETH_P_LINK_CTL 0x886c /* HPNA, wlan link local tunnel */ +#define ETH_P_8021AC 0x8870 /* 802.1AC LLC > 1500 bytes */ #define ETH_P_ATMFATE 0x8884 /* Frame-based ATM Transport * over Ethernet */ @@ -164,6 +165,10 @@ #define ETH_P_MCTP 0x00FA /* Management component transport * protocol packets */ +#define ETH_P_GRE_OSI 0x00FE /* GRE tunnels: LLC "fe fe 03" analog, + * used primarily for IS-IS over GRE + * WARNING: not internal, used on wire! + */ /* * This is an Ethernet frame header. -- cgit v1.3-14-g43fede From 103ff3a50e3a50a97e2b123d4dccbc8665eb1552 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 9 Jun 2026 17:09:28 +0200 Subject: KVM: s390: Add capability to support 2G hugepages Add KVM_CAP_S390_HPAGE_2G to signal to userspace that 2G hugepages may be used to back the guest; restrictions apply similar to 1M hugepages. Enable the (for now still ignored) GMAP_FLAG_ALLOW_HPAGE_2G flag for the guest gmap, and propagate / disable it as necessary. Reviewed-by: Steffen Eiden Signed-off-by: Claudio Imbrenda Message-ID: <20260609150930.665370-3-imbrenda@linux.ibm.com> --- arch/s390/kvm/gmap.c | 5 +++++ arch/s390/kvm/kvm-s390.c | 26 ++++++++++++++++++++++++++ arch/s390/kvm/pv.c | 5 ++++- include/uapi/linux/kvm.h | 1 + 4 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c index fe138d17caaf..f8bd6c135e3c 100644 --- a/arch/s390/kvm/gmap.c +++ b/arch/s390/kvm/gmap.c @@ -105,6 +105,11 @@ static void gmap_add_child(struct gmap *parent, struct gmap *child) else clear_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &child->flags); + if (test_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &parent->flags)) + set_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &child->flags); + else + clear_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &child->flags); + if (kvm_is_ucontrol(parent->kvm)) clear_bit(GMAP_FLAG_OWNS_PAGETABLES, &child->flags); list_add(&child->list, &parent->children); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index abc7941d7bb4..6de36421548c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -646,6 +646,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) if (hpage && !(kvm && kvm_is_ucontrol(kvm))) r = 1; break; + case KVM_CAP_S390_HPAGE_2G: + r = 0; + if (hpage_2g && !(kvm && kvm_is_ucontrol(kvm))) + r = 1; + break; case KVM_CAP_S390_MEM_OP: r = MEM_OP_MAX_SIZE; break; @@ -902,6 +907,27 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s", r ? "(not available)" : "(success)"); break; + case KVM_CAP_S390_HPAGE_2G: + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) { + r = -EBUSY; + } else if (!hpage_2g || kvm->arch.use_cmma || kvm_is_ucontrol(kvm)) { + r = -EINVAL; + } else { + r = 0; + set_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &kvm->arch.gmap->flags); + /* + * We might have to create fake 4k page + * tables. To avoid that the hardware works on + * stale PGSTEs, we emulate these instructions. + */ + kvm->arch.use_skf = 0; + kvm->arch.use_pfmfi = 0; + } + mutex_unlock(&kvm->lock); + VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE_2G %s", + r ? "(not available)" : "(success)"); + break; case KVM_CAP_S390_USER_STSI: VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI"); kvm->arch.user_stsi = 1; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index c2dafd812a3b..b9a23df96f7d 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -721,7 +721,10 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) uvcb.flags.ap_allow_instr = kvm->arch.model.uv_feat_guest.ap; uvcb.flags.ap_instr_intr = kvm->arch.model.uv_feat_guest.ap_intr; - clear_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &kvm->arch.gmap->flags); + scoped_guard(write_lock, &kvm->mmu_lock) { + clear_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &kvm->arch.gmap->flags); + clear_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &kvm->arch.gmap->flags); + } gmap_split_huge_pages(kvm->arch.gmap); cc = uv_call_sched(0, (u64)&uvcb); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6c8afa2047bf..419011097fa8 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -996,6 +996,7 @@ struct kvm_enable_cap { #define KVM_CAP_S390_USER_OPEREXEC 246 #define KVM_CAP_S390_KEYOP 247 #define KVM_CAP_S390_VSIE_ESAMODE 248 +#define KVM_CAP_S390_HPAGE_2G 249 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.3-14-g43fede From 978cda83de411fcbff22ac5b2b0024cae7df806f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 19 Apr 2026 14:53:02 -0400 Subject: NFSD: Add NFSD_CMD_UNLOCK_IP netlink command The existing write_unlock_ip procfs interface releases NLM file locks held by a specific client IP address, but procfs provides no structured way to extend that operation to other scopes such as revoking NFSv4 state. Add NFSD_CMD_UNLOCK_IP as a dedicated netlink command for releasing NLM locks by client address. The command accepts a binary sockaddr_in or sockaddr_in6 in its address attribute. The handler validates the address family and length, then calls nlmsvc_unlock_all_by_ip() to release matching NLM locks. Because lockd is a single global instance, that call operates across all network namespaces regardless of which namespace the caller inhabits. A separate netlink command for filesystem-scoped unlock is added in a subsequent commit. The nfsd_ctl_unlock_ip tracepoint is updated from string-based address logging to __sockaddr, which stores the binary sockaddr and formats it with %pISpc. This affects both the new netlink path and the existing procfs write_unlock_ip path, giving consistent structured output in both cases. Reviewed-by: Jeff Layton Tested-by: Dai Ngo Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 18 ++++++++++++++++ fs/nfsd/netlink.c | 12 +++++++++++ fs/nfsd/netlink.h | 1 + fs/nfsd/nfsctl.c | 40 ++++++++++++++++++++++++++++++++++- fs/nfsd/trace.h | 13 ++++++------ include/uapi/linux/nfsd_netlink.h | 8 +++++++ 6 files changed, 85 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 25497b533185..bf41682464c3 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -301,6 +301,15 @@ attribute-sets: type: u32 enum: cache-type enum-as-flags: true + - + name: unlock-ip + attributes: + - + name: address + type: binary + doc: struct sockaddr_in or struct sockaddr_in6. + checks: + min-len: 16 operations: list: @@ -455,6 +464,15 @@ operations: request: attributes: - mask + - + name: unlock-ip + doc: release NLM locks held by an IP address + attribute-set: unlock-ip + flags: [admin-perm] + do: + request: + attributes: + - address mcast-groups: list: diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index f99add477cc7..5830627c0288 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -103,6 +103,11 @@ static const struct nla_policy nfsd_cache_flush_nl_policy[NFSD_A_CACHE_FLUSH_MAS [NFSD_A_CACHE_FLUSH_MASK] = NLA_POLICY_MASK(NLA_U32, 0x3), }; +/* NFSD_CMD_UNLOCK_IP - do */ +static const struct nla_policy nfsd_unlock_ip_nl_policy[NFSD_A_UNLOCK_IP_ADDRESS + 1] = { + [NFSD_A_UNLOCK_IP_ADDRESS] = NLA_POLICY_MIN_LEN(16), +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -189,6 +194,13 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .maxattr = NFSD_A_CACHE_FLUSH_MASK, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_UNLOCK_IP, + .doit = nfsd_nl_unlock_ip_doit, + .policy = nfsd_unlock_ip_nl_policy, + .maxattr = NFSD_A_UNLOCK_IP_ADDRESS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group nfsd_nl_mcgrps[] = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index cc89732ed71b..88edbbc68453 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -39,6 +39,7 @@ int nfsd_nl_expkey_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int nfsd_nl_expkey_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_unlock_ip_doit(struct sk_buff *skb, struct genl_info *info); enum { NFSD_NLGRP_NONE, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index bfb937e8ad7c..cf246652e478 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -247,7 +247,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) if (rpc_pton(net, fo_path, size, sap, salen) == 0) return -EINVAL; - trace_nfsd_ctl_unlock_ip(net, buf); + trace_nfsd_ctl_unlock_ip(net, sap, svc_addr_len(sap)); return nlmsvc_unlock_all_by_ip(sap); } @@ -2276,6 +2276,44 @@ int nfsd_cache_notify(struct cache_detail *cd, struct cache_head *h, u32 cache_t NFSD_NLGRP_EXPORTD, GFP_KERNEL); } +/** + * nfsd_nl_unlock_ip_doit - release NLM locks held by an IP address + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return: 0 on success or a negative errno. + */ +int nfsd_nl_unlock_ip_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct sockaddr *sap; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_UNLOCK_IP_ADDRESS)) + return -EINVAL; + sap = nla_data(info->attrs[NFSD_A_UNLOCK_IP_ADDRESS]); + switch (sap->sa_family) { + case AF_INET: + if (nla_len(info->attrs[NFSD_A_UNLOCK_IP_ADDRESS]) < + sizeof(struct sockaddr_in)) + return -EINVAL; + break; + case AF_INET6: + if (nla_len(info->attrs[NFSD_A_UNLOCK_IP_ADDRESS]) < + sizeof(struct sockaddr_in6)) + return -EINVAL; + break; + default: + return -EAFNOSUPPORT; + } + /* + * nlmsvc_unlock_all_by_ip() releases matching locks + * across all network namespaces because lockd operates + * a single global instance. + */ + trace_nfsd_ctl_unlock_ip(genl_info_net(info), sap, + svc_addr_len(sap)); + return nlmsvc_unlock_all_by_ip(sap); +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index b631a472222b..9a73e7a1acf2 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -1985,19 +1985,20 @@ TRACE_EVENT(nfsd_cb_recall_any_done, TRACE_EVENT(nfsd_ctl_unlock_ip, TP_PROTO( const struct net *net, - const char *address + const struct sockaddr *addr, + const unsigned int addrlen ), - TP_ARGS(net, address), + TP_ARGS(net, addr, addrlen), TP_STRUCT__entry( __field(unsigned int, netns_ino) - __string(address, address) + __sockaddr(addr, addrlen) ), TP_fast_assign( __entry->netns_ino = net->ns.inum; - __assign_str(address); + __assign_sockaddr(addr, addr, addrlen); ), - TP_printk("address=%s", - __get_str(address) + TP_printk("addr=%pISpc", + __get_sockaddr(addr) ) ); diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 060c43675599..90ef1e686769 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -204,6 +204,13 @@ enum { NFSD_A_CACHE_FLUSH_MAX = (__NFSD_A_CACHE_FLUSH_MAX - 1) }; +enum { + NFSD_A_UNLOCK_IP_ADDRESS = 1, + + __NFSD_A_UNLOCK_IP_MAX, + NFSD_A_UNLOCK_IP_MAX = (__NFSD_A_UNLOCK_IP_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, @@ -220,6 +227,7 @@ enum { NFSD_CMD_EXPKEY_GET_REQS, NFSD_CMD_EXPKEY_SET_REQS, NFSD_CMD_CACHE_FLUSH, + NFSD_CMD_UNLOCK_IP, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.3-14-g43fede From 327c5168eff2e7f1760ca67fcb0f9053019fbfee Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 19 Apr 2026 14:53:03 -0400 Subject: NFSD: Add NFSD_CMD_UNLOCK_FILESYSTEM netlink command Add NFSD_CMD_UNLOCK_FILESYSTEM as a dedicated netlink command for revoking NFS state under a filesystem path, providing a netlink equivalent of /proc/fs/nfsd/unlock_fs. The command requires a "path" string attribute containing the filesystem path whose state should be released. The handler resolves the path to its superblock, then cancels async copies, releases NLM locks, and revokes NFSv4 state on that superblock. Reviewed-by: Jeff Layton Tested-by: Dai Ngo Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 16 ++++++++++++++ fs/nfsd/netlink.c | 12 +++++++++++ fs/nfsd/netlink.h | 1 + fs/nfsd/nfsctl.c | 40 +++++++++++++++++++++++++++++++++++ include/uapi/linux/nfsd_netlink.h | 8 +++++++ 5 files changed, 77 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index bf41682464c3..e121c54033a0 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -310,6 +310,13 @@ attribute-sets: doc: struct sockaddr_in or struct sockaddr_in6. checks: min-len: 16 + - + name: unlock-filesystem + attributes: + - + name: path + type: string + doc: Filesystem path whose state should be released. operations: list: @@ -473,6 +480,15 @@ operations: request: attributes: - address + - + name: unlock-filesystem + doc: revoke NFS state under a filesystem path + attribute-set: unlock-filesystem + flags: [admin-perm] + do: + request: + attributes: + - path mcast-groups: list: diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index 5830627c0288..63df3c4cf63a 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -108,6 +108,11 @@ static const struct nla_policy nfsd_unlock_ip_nl_policy[NFSD_A_UNLOCK_IP_ADDRESS [NFSD_A_UNLOCK_IP_ADDRESS] = NLA_POLICY_MIN_LEN(16), }; +/* NFSD_CMD_UNLOCK_FILESYSTEM - do */ +static const struct nla_policy nfsd_unlock_filesystem_nl_policy[NFSD_A_UNLOCK_FILESYSTEM_PATH + 1] = { + [NFSD_A_UNLOCK_FILESYSTEM_PATH] = { .type = NLA_NUL_STRING, }, +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -201,6 +206,13 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .maxattr = NFSD_A_UNLOCK_IP_ADDRESS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_UNLOCK_FILESYSTEM, + .doit = nfsd_nl_unlock_filesystem_doit, + .policy = nfsd_unlock_filesystem_nl_policy, + .maxattr = NFSD_A_UNLOCK_FILESYSTEM_PATH, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group nfsd_nl_mcgrps[] = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index 88edbbc68453..29bd5468d401 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -40,6 +40,7 @@ int nfsd_nl_expkey_get_reqs_dumpit(struct sk_buff *skb, int nfsd_nl_expkey_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_unlock_ip_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_unlock_filesystem_doit(struct sk_buff *skb, struct genl_info *info); enum { NFSD_NLGRP_NONE, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index cf246652e478..f7f104cc457d 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2314,6 +2314,46 @@ int nfsd_nl_unlock_ip_doit(struct sk_buff *skb, struct genl_info *info) return nlmsvc_unlock_all_by_ip(sap); } +/** + * nfsd_nl_unlock_filesystem_doit - revoke NFS state under a filesystem path + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return: 0 on success or a negative errno. + */ +int nfsd_nl_unlock_filesystem_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct path path; + int error; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_UNLOCK_FILESYSTEM_PATH)) + return -EINVAL; + + trace_nfsd_ctl_unlock_fs(net, + nla_data(info->attrs[NFSD_A_UNLOCK_FILESYSTEM_PATH])); + error = kern_path( + nla_data(info->attrs[NFSD_A_UNLOCK_FILESYSTEM_PATH]), + 0, &path); + if (error) + return error; + + nfsd4_cancel_copy_by_sb(net, path.dentry->d_sb); + error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb); + + mutex_lock(&nfsd_mutex); + if (nn->nfsd_serv) + nfsd4_revoke_states(nn, path.dentry->d_sb); + else + error = -EINVAL; + mutex_unlock(&nfsd_mutex); + + path_put(&path); + return error; +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 90ef1e686769..d01096c06d72 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -211,6 +211,13 @@ enum { NFSD_A_UNLOCK_IP_MAX = (__NFSD_A_UNLOCK_IP_MAX - 1) }; +enum { + NFSD_A_UNLOCK_FILESYSTEM_PATH = 1, + + __NFSD_A_UNLOCK_FILESYSTEM_MAX, + NFSD_A_UNLOCK_FILESYSTEM_MAX = (__NFSD_A_UNLOCK_FILESYSTEM_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, @@ -228,6 +235,7 @@ enum { NFSD_CMD_EXPKEY_SET_REQS, NFSD_CMD_CACHE_FLUSH, NFSD_CMD_UNLOCK_IP, + NFSD_CMD_UNLOCK_FILESYSTEM, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.3-14-g43fede From 2eac189bb059d31a29937b29ee0f477394198610 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 19 Apr 2026 14:53:06 -0400 Subject: NFSD: Add NFSD_CMD_UNLOCK_EXPORT netlink command When a filesystem is exported to NFS clients, NFSv4 state (opens, locks, delegations, layouts) holds references that prevent the underlying filesystem from being unmounted. NFSD_CMD_UNLOCK_FILESYSTEM addresses this at superblock granularity, but administrators unexporting a single path on a shared filesystem (e.g., one of several exports on the same device) need finer control. Add NFSD_CMD_UNLOCK_EXPORT, which revokes NFSv4 state acquired through exports of a specific path. Matching is by path identity (dentry + vfsmount) via the sc_export field on each nfs4_stid, so multiple svc_export objects for the same path -- one per auth_domain -- are handled correctly without requiring the caller to name a specific client. The command takes a single "path" attribute. Userspace (exportfs -u) sends this after removing the last client for a given path, enabling the underlying filesystem to be unmounted. When multiple clients share an export path, individual unexports do not trigger state revocation; only the final one does. Reviewed-by: Jeff Layton Tested-by: Dai Ngo Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 27 ++++++++++++++ fs/nfsd/netlink.c | 12 +++++++ fs/nfsd/netlink.h | 1 + fs/nfsd/nfs4state.c | 67 +++++++++++++++++++++++++++++++++++ fs/nfsd/nfsctl.c | 45 +++++++++++++++++++++++ fs/nfsd/state.h | 5 +++ fs/nfsd/trace.h | 19 ++++++++++ include/uapi/linux/nfsd_netlink.h | 8 +++++ 8 files changed, 184 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index e121c54033a0..8f36fadd68f7 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -317,6 +317,19 @@ attribute-sets: name: path type: string doc: Filesystem path whose state should be released. + - + name: unlock-export + attributes: + - + name: path + type: string + doc: >- + Export path whose NFSv4 state should be revoked. + All state (opens, locks, delegations, layouts) acquired + through any export of this path is revoked, regardless + of which client holds the state. Intended for use after + all clients have been unexported from a given path, + enabling the underlying filesystem to be unmounted. operations: list: @@ -489,6 +502,20 @@ operations: request: attributes: - path + - + name: unlock-export + doc: >- + Revoke NFSv4 state acquired through exports of a given path. + Unlike unlock-filesystem, which operates at superblock granularity, + this command targets only state associated with a specific export + path. Userspace (exportfs -u) sends this after removing the last + client for a path so the underlying filesystem can be unmounted. + attribute-set: unlock-export + flags: [admin-perm] + do: + request: + attributes: + - path mcast-groups: list: diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index 63df3c4cf63a..fbee3676d253 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -113,6 +113,11 @@ static const struct nla_policy nfsd_unlock_filesystem_nl_policy[NFSD_A_UNLOCK_FI [NFSD_A_UNLOCK_FILESYSTEM_PATH] = { .type = NLA_NUL_STRING, }, }; +/* NFSD_CMD_UNLOCK_EXPORT - do */ +static const struct nla_policy nfsd_unlock_export_nl_policy[NFSD_A_UNLOCK_EXPORT_PATH + 1] = { + [NFSD_A_UNLOCK_EXPORT_PATH] = { .type = NLA_NUL_STRING, }, +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -213,6 +218,13 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .maxattr = NFSD_A_UNLOCK_FILESYSTEM_PATH, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_UNLOCK_EXPORT, + .doit = nfsd_nl_unlock_export_doit, + .policy = nfsd_unlock_export_nl_policy, + .maxattr = NFSD_A_UNLOCK_EXPORT_PATH, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group nfsd_nl_mcgrps[] = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index 29bd5468d401..af41aa0d4a65 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -41,6 +41,7 @@ int nfsd_nl_expkey_set_reqs_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_unlock_ip_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_unlock_filesystem_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_unlock_export_doit(struct sk_buff *skb, struct genl_info *info); enum { NFSD_NLGRP_NONE, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 475d2b36ecd1..2cf021b202a6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1911,6 +1911,73 @@ void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) spin_unlock(&nn->client_lock); } +static struct nfs4_stid *find_one_export_stid(struct nfs4_client *clp, + const struct path *path, + unsigned int sc_types) +{ + unsigned long id = 0; + struct nfs4_stid *stid; + + spin_lock(&clp->cl_lock); + while ((stid = idr_get_next_ul(&clp->cl_stateids, &id)) != NULL) { + if ((stid->sc_type & sc_types) && + stid->sc_status == 0 && + stid->sc_export && + path_equal(&stid->sc_export->ex_path, path)) { + refcount_inc(&stid->sc_count); + break; + } + id++; + } + spin_unlock(&clp->cl_lock); + return stid; +} + +/** + * nfsd4_revoke_export_states - revoke nfsv4 states acquired through an export + * @nn: used to identify instance of nfsd (there is one per net namespace) + * @path: export path whose states should be revoked + * + * All nfs4 states (open, lock, delegation, layout) acquired through any + * export matching @path are revoked, regardless of which client holds + * them. Matching is by path identity (dentry + vfsmount), so multiple + * svc_export objects for the same path -- one per auth_domain -- are + * handled correctly. + * + * Userspace (exportfs -u) sends this after removing the last client + * for a path, enabling the underlying filesystem to be unmounted. + */ +void nfsd4_revoke_export_states(struct nfsd_net *nn, const struct path *path) +{ + unsigned int idhashval; + unsigned int sc_types; + + sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; + + spin_lock(&nn->client_lock); + for (idhashval = 0; idhashval < CLIENT_HASH_SIZE; idhashval++) { + struct list_head *head = &nn->conf_id_hashtbl[idhashval]; + struct nfs4_client *clp; + retry: + list_for_each_entry(clp, head, cl_idhash) { + struct nfs4_stid *stid = find_one_export_stid( + clp, path, + sc_types); + if (stid) { + spin_unlock(&nn->client_lock); + revoke_one_stid(nn, clp, stid); + nfs4_put_stid(stid); + spin_lock(&nn->client_lock); + if (clp->cl_minorversion == 0) + nn->nfs40_last_revoke = + ktime_get_boottime_seconds(); + goto retry; + } + } + } + spin_unlock(&nn->client_lock); +} + static inline int hash_sessionid(struct nfs4_sessionid *sessionid) { diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index f7f104cc457d..dd4fb9249213 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2354,6 +2354,51 @@ int nfsd_nl_unlock_filesystem_doit(struct sk_buff *skb, return error; } +/** + * nfsd_nl_unlock_export_doit - revoke NFSv4 state for an export path + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Revokes all NFSv4 state (opens, locks, delegations, layouts) acquired + * through any export of the given path, regardless of which client holds + * the state. Userspace (exportfs -u) sends this after removing the last + * client for a path so the underlying filesystem can be unmounted. + * + * Unlike NFSD_CMD_UNLOCK_FILESYSTEM, which operates at superblock + * granularity, this command revokes only the state associated with + * exports of a specific path. + * + * Return: 0 on success or a negative errno. + */ +int nfsd_nl_unlock_export_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct path path; + int error; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_UNLOCK_EXPORT_PATH)) + return -EINVAL; + + trace_nfsd_ctl_unlock_export(net, + nla_data(info->attrs[NFSD_A_UNLOCK_EXPORT_PATH])); + error = kern_path( + nla_data(info->attrs[NFSD_A_UNLOCK_EXPORT_PATH]), + 0, &path); + if (error) + return error; + + mutex_lock(&nfsd_mutex); + if (nn->nfsd_serv) + nfsd4_revoke_export_states(nn, &path); + else + error = -EINVAL; + mutex_unlock(&nfsd_mutex); + + path_put(&path); + return error; +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 43bd965077e1..dec83e92650d 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -863,6 +863,7 @@ struct nfsd_file *find_any_file(struct nfs4_file *f); #ifdef CONFIG_NFSD_V4 void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb); +void nfsd4_revoke_export_states(struct nfsd_net *nn, const struct path *path); void nfsd4_cancel_copy_by_sb(struct net *net, struct super_block *sb); int nfsd_net_cb_init(struct nfsd_net *nn); void nfsd_net_cb_shutdown(struct nfsd_net *nn); @@ -870,6 +871,10 @@ void nfsd_net_cb_shutdown(struct nfsd_net *nn); static inline void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) { } +static inline void nfsd4_revoke_export_states(struct nfsd_net *nn, + const struct path *path) +{ +} static inline void nfsd4_cancel_copy_by_sb(struct net *net, struct super_block *sb) { } diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 9a73e7a1acf2..1c5a1e50f946 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -2021,6 +2021,25 @@ TRACE_EVENT(nfsd_ctl_unlock_fs, ) ); +TRACE_EVENT(nfsd_ctl_unlock_export, + TP_PROTO( + const struct net *net, + const char *path + ), + TP_ARGS(net, path), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(path, path) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(path); + ), + TP_printk("path=%s", + __get_str(path) + ) +); + TRACE_EVENT(nfsd_ctl_filehandle, TP_PROTO( const struct net *net, diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index d01096c06d72..f5b75d5caba9 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -218,6 +218,13 @@ enum { NFSD_A_UNLOCK_FILESYSTEM_MAX = (__NFSD_A_UNLOCK_FILESYSTEM_MAX - 1) }; +enum { + NFSD_A_UNLOCK_EXPORT_PATH = 1, + + __NFSD_A_UNLOCK_EXPORT_MAX, + NFSD_A_UNLOCK_EXPORT_MAX = (__NFSD_A_UNLOCK_EXPORT_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, @@ -236,6 +243,7 @@ enum { NFSD_CMD_CACHE_FLUSH, NFSD_CMD_UNLOCK_IP, NFSD_CMD_UNLOCK_FILESYSTEM, + NFSD_CMD_UNLOCK_EXPORT, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.3-14-g43fede From 02687282c751a77b774e4a16d5e937c3ecd1731d Mon Sep 17 00:00:00 2001 From: Ethan Carter Edwards Date: Sat, 18 Apr 2026 20:49:48 -0400 Subject: virtio_console: Fix spelling mistake "colums" -> "columns" There is a spelling mistake in a struct description. Fix it. Signed-off-by: Ethan Carter Edwards Signed-off-by: Michael S. Tsirkin Message-ID: <20260418-virtio-typo-v1-1-0df6f943a79d@ethancedwards.com> --- include/uapi/linux/virtio_console.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_console.h b/include/uapi/linux/virtio_console.h index 7e6ec2ff0560..0506539e6553 100644 --- a/include/uapi/linux/virtio_console.h +++ b/include/uapi/linux/virtio_console.h @@ -44,7 +44,7 @@ #define VIRTIO_CONSOLE_BAD_ID (~(__u32)0) struct virtio_console_config { - /* colums of the screens */ + /* columns of the screens */ __virtio16 cols; /* rows of the screens */ __virtio16 rows; -- cgit v1.3-14-g43fede From 083082a4e6d8311c91ac7e1d59426514c5e1c04b Mon Sep 17 00:00:00 2001 From: Matias Ezequiel Vara Larsen Date: Tue, 26 May 2026 18:42:23 +0200 Subject: can: virtio: Add virtio CAN driver Add virtio CAN driver based on Virtio 1.4 specification (see https://github.com/oasis-tcs/virtio-spec/tree/virtio-1.4). The driver implements a complete CAN bus interface over Virtio transport, supporting both CAN Classic and CAN-FD Ids. In term of frames, it supports classic and CAN FD. RTR frames are only supported with classic CAN. Usage: - "ip link set up can0" - start controller - "ip link set down can0" - stop controller - "candump can0" - receive frames - "cansend can0 123#DEADBEEF" - send frames Signed-off-by: Harald Mommer Co-developed-by: Harald Mommer Signed-off-by: Mikhail Golubev-Ciuchea Co-developed-by: Marc Kleine-Budde Signed-off-by: Marc Kleine-Budde Cc: Damir Shaikhutdinov Reviewed-by: Francesco Valla Tested-by: Francesco Valla Signed-off-by: Matias Ezequiel Vara Larsen Signed-off-by: Michael S. Tsirkin Message-ID: --- MAINTAINERS | 9 + drivers/net/can/Kconfig | 12 + drivers/net/can/Makefile | 1 + drivers/net/can/virtio_can.c | 1022 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/virtio_can.h | 78 +++ 5 files changed, 1122 insertions(+) create mode 100644 drivers/net/can/virtio_can.c create mode 100644 include/uapi/linux/virtio_can.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 9ec290e38b44..e7bd5e40eb5b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -28196,6 +28196,15 @@ F: drivers/scsi/virtio_scsi.c F: include/uapi/linux/virtio_blk.h F: include/uapi/linux/virtio_scsi.h +VIRTIO CAN DRIVER +M: "Harald Mommer" +M: "Matias Ezequiel Vara Larsen" +L: virtualization@lists.linux.dev +L: linux-can@vger.kernel.org +S: Maintained +F: drivers/net/can/virtio_can.c +F: include/uapi/linux/virtio_can.h + VIRTIO CONSOLE DRIVER M: Amit Shah L: virtualization@lists.linux.dev diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index e15e320db476..e4058708ae68 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -226,6 +226,18 @@ config CAN_TI_HECC Driver for TI HECC (High End CAN Controller) module found on many TI devices. The device specifications are available from www.ti.com +config CAN_VIRTIO_CAN + depends on VIRTIO + tristate "Virtio CAN device support" + default n + help + Say Y here if you want to support for Virtio CAN. + + To compile this driver as a module, choose M here: the + module will be called virtio-can. + + If unsure, say N. + config CAN_XILINXCAN tristate "Xilinx CAN" depends on ARCH_ZYNQ || ARM64 || MICROBLAZE || COMPILE_TEST diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index d7bc10a6b8ea..4010d17f8583 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -33,6 +33,7 @@ obj-$(CONFIG_CAN_PEAK_PCIEFD) += peak_canfd/ obj-$(CONFIG_CAN_SJA1000) += sja1000/ obj-$(CONFIG_CAN_SUN4I) += sun4i_can.o obj-$(CONFIG_CAN_TI_HECC) += ti_hecc.o +obj-$(CONFIG_CAN_VIRTIO_CAN) += virtio_can.o obj-$(CONFIG_CAN_XILINXCAN) += xilinx_can.o subdir-ccflags-$(CONFIG_CAN_DEBUG_DEVICES) += -DDEBUG diff --git a/drivers/net/can/virtio_can.c b/drivers/net/can/virtio_can.c new file mode 100644 index 000000000000..f67d0bf09681 --- /dev/null +++ b/drivers/net/can/virtio_can.c @@ -0,0 +1,1022 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * CAN bus driver for the Virtio CAN controller + * + * Copyright (C) 2021-2023 OpenSynergy GmbH + * Copyright Red Hat, Inc. 2025 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* CAN device queues */ +#define VIRTIO_CAN_QUEUE_TX 0 +#define VIRTIO_CAN_QUEUE_RX 1 +#define VIRTIO_CAN_QUEUE_CONTROL 2 +#define VIRTIO_CAN_QUEUE_COUNT 3 + +#define CAN_KNOWN_FLAGS \ + (VIRTIO_CAN_FLAGS_EXTENDED |\ + VIRTIO_CAN_FLAGS_FD |\ + VIRTIO_CAN_FLAGS_RTR) + +/* Max. number of in flight TX messages */ +#define VIRTIO_CAN_ECHO_SKB_MAX 128 + +struct virtio_can_tx { + unsigned int putidx; + struct virtio_can_tx_in tx_in; + /* Keep virtio_can_tx_out at the end of the structure due to flex array */ + struct virtio_can_tx_out tx_out; +}; + +struct virtio_can_control { + struct virtio_can_control_out cpkt_out; + struct virtio_can_control_in cpkt_in; +}; + +/* virtio_can private data structure */ +struct virtio_can_priv { + struct can_priv can; /* must be the first member */ + /* NAPI for RX messages */ + struct napi_struct napi; + /* NAPI for TX messages */ + struct napi_struct napi_tx; + /* The network device we're associated with */ + struct net_device *dev; + /* The virtio device we're associated with */ + struct virtio_device *vdev; + /* The virtqueues */ + struct virtqueue *vqs[VIRTIO_CAN_QUEUE_COUNT]; + /* Lock for TX operations */ + spinlock_t tx_lock; + /* Control queue lock */ + struct mutex ctrl_lock; + /* Wait for control queue processing without polling */ + struct completion ctrl_done; + /* Array of receive queue messages */ + struct virtio_can_rx *rpkt; + struct virtio_can_control can_ctr_msg; + /* Data to get and maintain the putidx for local TX echo */ + struct ida tx_putidx_ida; + /* In flight TX messages */ + atomic_t tx_inflight; + /* Packet length */ + int rpkt_len; + /* BusOff pending. Reset after successful indication to upper layer */ + bool busoff_pending; + /* Tracks whether NAPI instances are currently enabled */ + bool napi_active; +}; + +static void virtqueue_napi_schedule(struct napi_struct *napi, + struct virtqueue *vq) +{ + if (napi_schedule_prep(napi)) { + virtqueue_disable_cb(vq); + __napi_schedule(napi); + } +} + +static void virtqueue_napi_complete(struct napi_struct *napi, + struct virtqueue *vq, int processed) +{ + int opaque; + + opaque = virtqueue_enable_cb_prepare(vq); + if (napi_complete_done(napi, processed)) { + if (unlikely(virtqueue_poll(vq, opaque))) + virtqueue_napi_schedule(napi, vq); + } else { + virtqueue_disable_cb(vq); + } +} + +static void virtio_can_free_candev(struct net_device *ndev) +{ + struct virtio_can_priv *priv = netdev_priv(ndev); + + ida_destroy(&priv->tx_putidx_ida); + free_candev(ndev); +} + +static void virtio_can_napi_enable(struct virtio_can_priv *priv) +{ + if (!priv->napi_active) { + napi_enable(&priv->napi); + napi_enable(&priv->napi_tx); + priv->napi_active = true; + } +} + +static void virtio_can_napi_disable(struct virtio_can_priv *priv) +{ + if (priv->napi_active) { + napi_disable(&priv->napi_tx); + napi_disable(&priv->napi); + priv->napi_active = false; + } +} + +static int virtio_can_alloc_tx_idx(struct virtio_can_priv *priv) +{ + int tx_idx; + + tx_idx = ida_alloc_max(&priv->tx_putidx_ida, + priv->can.echo_skb_max - 1, GFP_ATOMIC); + if (tx_idx >= 0) + atomic_inc(&priv->tx_inflight); + + return tx_idx; +} + +static void virtio_can_free_tx_idx(struct virtio_can_priv *priv, + unsigned int idx) +{ + ida_free(&priv->tx_putidx_ida, idx); + atomic_dec(&priv->tx_inflight); +} + +/* Create a scatter-gather list representing our input buffer and put + * it in the queue. + * + * Callers should take appropriate locks. + */ +static int virtio_can_add_inbuf(struct virtqueue *vq, void *buf, + unsigned int size) +{ + struct scatterlist sg[1]; + int ret; + + sg_init_one(sg, buf, size); + + ret = virtqueue_add_inbuf(vq, sg, 1, buf, GFP_ATOMIC); + + return ret; +} + +/* Send a control message with message type either + * + * - VIRTIO_CAN_SET_CTRL_MODE_START or + * - VIRTIO_CAN_SET_CTRL_MODE_STOP. + * + */ +static u8 virtio_can_send_ctrl_msg(struct net_device *ndev, u16 msg_type) +{ + struct scatterlist sg_out, sg_in, *sgs[2] = { &sg_out, &sg_in }; + struct virtio_can_priv *priv = netdev_priv(ndev); + struct virtqueue *vq = priv->vqs[VIRTIO_CAN_QUEUE_CONTROL]; + struct device *dev = &priv->vdev->dev; + unsigned int len; + int err; + + if (!vq) + return VIRTIO_CAN_RESULT_NOT_OK; + + guard(mutex)(&priv->ctrl_lock); + + priv->can_ctr_msg.cpkt_out.msg_type = cpu_to_le16(msg_type); + sg_init_one(&sg_out, &priv->can_ctr_msg.cpkt_out, + sizeof(priv->can_ctr_msg.cpkt_out)); + sg_init_one(&sg_in, &priv->can_ctr_msg.cpkt_in, sizeof(priv->can_ctr_msg.cpkt_in)); + + reinit_completion(&priv->ctrl_done); + + err = virtqueue_add_sgs(vq, sgs, 1u, 1u, priv, GFP_ATOMIC); + if (err != 0) { + dev_err(dev, "%s(): virtqueue_add_sgs() failed\n", __func__); + return VIRTIO_CAN_RESULT_NOT_OK; + } + + if (!virtqueue_kick(vq)) { + dev_err(dev, "%s(): Kick failed\n", __func__); + return VIRTIO_CAN_RESULT_NOT_OK; + } + + while (!virtqueue_get_buf(vq, &len) && !virtqueue_is_broken(vq)) + wait_for_completion(&priv->ctrl_done); + + return priv->can_ctr_msg.cpkt_in.result; +} + +static int virtio_can_start(struct net_device *ndev) +{ + struct virtio_can_priv *priv = netdev_priv(ndev); + u8 result; + + result = virtio_can_send_ctrl_msg(ndev, VIRTIO_CAN_SET_CTRL_MODE_START); + if (result != VIRTIO_CAN_RESULT_OK) { + netdev_err(ndev, "CAN controller start failed\n"); + return -EIO; + } + + priv->busoff_pending = false; + priv->can.state = CAN_STATE_ERROR_ACTIVE; + + return 0; +} + +static int virtio_can_set_mode(struct net_device *dev, enum can_mode mode) +{ + int err; + + switch (mode) { + case CAN_MODE_START: + err = virtio_can_start(dev); + if (err) + return err; + netif_wake_queue(dev); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int virtio_can_open(struct net_device *ndev) +{ + struct virtio_can_priv *priv = netdev_priv(ndev); + int err; + + err = open_candev(ndev); + if (err) + return err; + + err = virtio_can_start(ndev); + if (err) { + close_candev(ndev); + return err; + } + + virtio_can_napi_enable(priv); + netif_start_queue(ndev); + + return 0; +} + +static int virtio_can_stop(struct net_device *ndev) +{ + struct virtio_can_priv *priv = netdev_priv(ndev); + struct device *dev = &priv->vdev->dev; + u8 result; + + result = virtio_can_send_ctrl_msg(ndev, VIRTIO_CAN_SET_CTRL_MODE_STOP); + if (result != VIRTIO_CAN_RESULT_OK) { + dev_err(dev, "CAN controller stop failed\n"); + return -EIO; + } + + priv->busoff_pending = false; + priv->can.state = CAN_STATE_STOPPED; + + /* Switch carrier off if device was connected to the bus */ + if (netif_carrier_ok(ndev)) + netif_carrier_off(ndev); + + return 0; +} + +static int virtio_can_close(struct net_device *dev) +{ + struct virtio_can_priv *priv = netdev_priv(dev); + + netif_stop_queue(dev); + /* Ignore stop error: ndo_stop must always complete cleanup regardless. + * virtio_can_stop() already logs the error if it fails. + */ + virtio_can_stop(dev); + virtio_can_napi_disable(priv); + close_candev(dev); + + return 0; +} + +static netdev_tx_t virtio_can_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct scatterlist sg_out, sg_in, *sgs[2] = { &sg_out, &sg_in }; + const unsigned int hdr_size = sizeof(struct virtio_can_tx_out); + struct canfd_frame *cf = (struct canfd_frame *)skb->data; + struct virtio_can_priv *priv = netdev_priv(dev); + struct virtqueue *vq = priv->vqs[VIRTIO_CAN_QUEUE_TX]; + netdev_tx_t xmit_ret = NETDEV_TX_OK; + struct virtio_can_tx *can_tx_msg; + u32 can_flags; + int putidx; + int err; + + if (can_dev_dropped_skb(dev, skb)) + goto kick; /* No way to return NET_XMIT_DROP here */ + + /* No local check for CAN_RTR_FLAG or FD frame against negotiated + * features. The device will reject those anyway if not supported. + */ + + can_tx_msg = kzalloc(sizeof(*can_tx_msg) + cf->len, GFP_ATOMIC); + if (!can_tx_msg) { + kfree_skb(skb); + dev->stats.tx_dropped++; + goto kick; /* No way to return NET_XMIT_DROP here */ + } + + can_tx_msg->tx_out.msg_type = cpu_to_le16(VIRTIO_CAN_TX); + can_tx_msg->tx_out.length = cpu_to_le16(cf->len); + can_flags = 0; + + if (cf->can_id & CAN_EFF_FLAG) { + can_flags |= VIRTIO_CAN_FLAGS_EXTENDED; + can_tx_msg->tx_out.can_id = cpu_to_le32(cf->can_id & CAN_EFF_MASK); + } else { + can_tx_msg->tx_out.can_id = cpu_to_le32(cf->can_id & CAN_SFF_MASK); + } + if (cf->can_id & CAN_RTR_FLAG) + can_flags |= VIRTIO_CAN_FLAGS_RTR; + else + memcpy(can_tx_msg->tx_out.sdu, cf->data, cf->len); + if (can_is_canfd_skb(skb)) + can_flags |= VIRTIO_CAN_FLAGS_FD; + + can_tx_msg->tx_out.flags = cpu_to_le32(can_flags); + + sg_init_one(&sg_out, &can_tx_msg->tx_out, hdr_size + cf->len); + sg_init_one(&sg_in, &can_tx_msg->tx_in, sizeof(can_tx_msg->tx_in)); + + putidx = virtio_can_alloc_tx_idx(priv); + + if (unlikely(putidx < 0)) { + /* -ENOMEM or -ENOSPC here. -ENOSPC should not be possible as + * tx_inflight >= can.echo_skb_max is checked in flow control + */ + WARN_ON_ONCE(putidx == -ENOSPC); + kfree(can_tx_msg); + kfree_skb(skb); + dev->stats.tx_dropped++; + goto kick; /* No way to return NET_XMIT_DROP here */ + } + + can_tx_msg->putidx = (unsigned int)putidx; + + /* Push loopback echo. Will be looped back on TX interrupt/TX NAPI */ + err = can_put_echo_skb(skb, dev, can_tx_msg->putidx, 0); + if (unlikely(err)) { + /* skb was already freed by can_put_echo_skb() on error */ + virtio_can_free_tx_idx(priv, can_tx_msg->putidx); + kfree(can_tx_msg); + dev->stats.tx_dropped++; + goto kick; + } + + /* Protect queue and list operations */ + scoped_guard(spinlock_irqsave, &priv->tx_lock) + err = virtqueue_add_sgs(vq, sgs, 1u, 1u, can_tx_msg, GFP_ATOMIC); + + if (unlikely(err)) { + /* + * can_put_echo_skb() already consumed skb via consume_skb(), + * so returning NETDEV_TX_BUSY would cause the stack to requeue + * a freed pointer. Drop the frame and return OK instead. + */ + can_free_echo_skb(dev, can_tx_msg->putidx, NULL); + virtio_can_free_tx_idx(priv, can_tx_msg->putidx); + netif_stop_queue(dev); + kfree(can_tx_msg); + dev->stats.tx_dropped++; + /* Expected never to be seen */ + netdev_warn(dev, "TX: Stop queue, err = %d\n", err); + goto kick; + } + + /* Normal flow control: stop queue when no transmission slots left */ + if (atomic_read(&priv->tx_inflight) >= priv->can.echo_skb_max || + vq->num_free == 0 || (vq->num_free < ARRAY_SIZE(sgs) && + !virtio_has_feature(vq->vdev, VIRTIO_RING_F_INDIRECT_DESC))) { + netif_stop_queue(dev); + netdev_dbg(dev, "TX: Normal stop queue\n"); + } + +kick: + if (netif_queue_stopped(dev) || !netdev_xmit_more()) { + scoped_guard(spinlock_irqsave, &priv->tx_lock) { + if (!virtqueue_kick(vq)) + netdev_err(dev, "%s(): Kick failed\n", __func__); + } + } + + return xmit_ret; +} + +static const struct net_device_ops virtio_can_netdev_ops = { + .ndo_open = virtio_can_open, + .ndo_stop = virtio_can_close, + .ndo_start_xmit = virtio_can_start_xmit, +}; + +static int register_virtio_can_dev(struct net_device *dev) +{ + dev->flags |= IFF_ECHO; /* we support local echo */ + dev->netdev_ops = &virtio_can_netdev_ops; + + return register_candev(dev); +} + +static int virtio_can_read_tx_queue(struct virtqueue *vq) +{ + struct virtio_can_priv *can_priv = vq->vdev->priv; + struct net_device *dev = can_priv->dev; + struct virtio_can_tx *can_tx_msg; + struct net_device_stats *stats; + unsigned int len; + u8 result; + + stats = &dev->stats; + + scoped_guard(spinlock_irqsave, &can_priv->tx_lock) + can_tx_msg = virtqueue_get_buf(vq, &len); + + if (!can_tx_msg) + return 0; + + if (unlikely(len < sizeof(struct virtio_can_tx_in))) { + netdev_err(dev, "TX ACK: Device sent no result code\n"); + result = VIRTIO_CAN_RESULT_NOT_OK; /* Keep things going */ + } else { + result = can_tx_msg->tx_in.result; + } + + if (can_priv->can.state < CAN_STATE_BUS_OFF) { + if (result != VIRTIO_CAN_RESULT_OK) { + struct can_frame *skb_cf; + struct sk_buff *skb = alloc_can_err_skb(dev, &skb_cf); + + if (skb) { + skb_cf->can_id |= CAN_ERR_CRTL; + skb_cf->data[1] |= CAN_ERR_CRTL_UNSPEC; + netif_rx(skb); + } + netdev_warn(dev, "TX ACK: Result = %u\n", result); + can_free_echo_skb(dev, can_tx_msg->putidx, NULL); + stats->tx_dropped++; + } else { + stats->tx_bytes += can_get_echo_skb(dev, can_tx_msg->putidx, + NULL); + stats->tx_packets++; + } + } else { + netdev_dbg(dev, "TX ACK: Controller inactive, drop echo\n"); + can_free_echo_skb(dev, can_tx_msg->putidx, NULL); + stats->tx_dropped++; + } + + virtio_can_free_tx_idx(can_priv, can_tx_msg->putidx); + + /* Flow control */ + if (netif_queue_stopped(dev)) { + netdev_dbg(dev, "TX ACK: Wake up stopped queue\n"); + netif_wake_queue(dev); + } + + kfree(can_tx_msg); + + return 1; /* Queue was not empty so there may be more data */ +} + +static int virtio_can_tx_poll(struct napi_struct *napi, int quota) +{ + struct net_device *dev = napi->dev; + struct virtio_can_priv *priv = netdev_priv(dev); + struct virtqueue *vq = priv->vqs[VIRTIO_CAN_QUEUE_TX]; + int work_done = 0; + + while (work_done < quota && virtio_can_read_tx_queue(vq) != 0) + work_done++; + + if (work_done < quota) + virtqueue_napi_complete(napi, vq, work_done); + + return work_done; +} + +static void virtio_can_tx_intr(struct virtqueue *vq) +{ + struct virtio_can_priv *can_priv = vq->vdev->priv; + + virtqueue_disable_cb(vq); + napi_schedule(&can_priv->napi_tx); +} + +/* This function is the NAPI RX poll function and NAPI guarantees that this + * function is not invoked simultaneously on multiple processors. + * Read a RX message from the used queue and sends it to the upper layer. + */ +static int virtio_can_read_rx_queue(struct virtqueue *vq) +{ + const unsigned int header_size = sizeof(struct virtio_can_rx); + struct virtio_can_priv *priv = vq->vdev->priv; + struct net_device *dev = priv->dev; + struct net_device_stats *stats; + struct virtio_can_rx *can_rx; + unsigned int transport_len; + struct canfd_frame *cf; + struct sk_buff *skb; + unsigned int len; + u32 can_flags; + u16 msg_type; + u32 can_id; + int ret; + + stats = &dev->stats; + + can_rx = virtqueue_get_buf(vq, &transport_len); + if (!can_rx) + return 0; /* No more data */ + + if (transport_len < header_size) { + netdev_warn(dev, "RX: Message too small\n"); + goto putback; + } + + if (priv->can.state >= CAN_STATE_ERROR_PASSIVE) { + netdev_dbg(dev, "%s(): Controller not active\n", __func__); + goto putback; + } + + msg_type = le16_to_cpu(can_rx->msg_type); + if (msg_type != VIRTIO_CAN_RX) { + netdev_warn(dev, "RX: Got unknown msg_type %04x\n", msg_type); + goto putback; + } + + len = le16_to_cpu(can_rx->length); + can_flags = le32_to_cpu(can_rx->flags); + can_id = le32_to_cpu(can_rx->can_id); + + if (can_flags & ~CAN_KNOWN_FLAGS) { + stats->rx_dropped++; + netdev_warn(dev, "RX: CAN Id 0x%08x: Invalid flags 0x%x\n", + can_id, can_flags); + goto putback; + } + + if (can_flags & VIRTIO_CAN_FLAGS_EXTENDED) { + can_id &= CAN_EFF_MASK; + can_id |= CAN_EFF_FLAG; + } else { + can_id &= CAN_SFF_MASK; + } + + if (can_flags & VIRTIO_CAN_FLAGS_RTR) { + if (!virtio_has_feature(vq->vdev, VIRTIO_CAN_F_RTR_FRAMES)) { + stats->rx_dropped++; + netdev_warn(dev, "RX: CAN Id 0x%08x: RTR not negotiated\n", + can_id); + goto putback; + } + if (can_flags & VIRTIO_CAN_FLAGS_FD) { + stats->rx_dropped++; + netdev_warn(dev, "RX: CAN Id 0x%08x: RTR with FD not possible\n", + can_id); + goto putback; + } + + if (len > 0xF) { + stats->rx_dropped++; + netdev_warn(dev, "RX: CAN Id 0x%08x: RTR with DLC > 0xF\n", + can_id); + goto putback; + } + + if (len > 0x8) + len = 0x8; + + can_id |= CAN_RTR_FLAG; + } + + if (transport_len < header_size + len) { + netdev_warn(dev, "RX: Message too small for payload\n"); + goto putback; + } + + if (can_flags & VIRTIO_CAN_FLAGS_FD) { + if (!virtio_has_feature(vq->vdev, VIRTIO_CAN_F_CAN_FD)) { + stats->rx_dropped++; + netdev_warn(dev, "RX: CAN Id 0x%08x: FD not negotiated\n", + can_id); + goto putback; + } + + if (len > CANFD_MAX_DLEN) + len = CANFD_MAX_DLEN; + + skb = alloc_canfd_skb(priv->dev, &cf); + } else { + if (!virtio_has_feature(vq->vdev, VIRTIO_CAN_F_CAN_CLASSIC)) { + stats->rx_dropped++; + netdev_warn(dev, "RX: CAN Id 0x%08x: classic not negotiated\n", + can_id); + goto putback; + } + + if (len > CAN_MAX_DLEN) + len = CAN_MAX_DLEN; + + skb = alloc_can_skb(priv->dev, (struct can_frame **)&cf); + } + if (!skb) { + stats->rx_dropped++; + netdev_warn(dev, "RX: No skb available\n"); + goto putback; + } + + cf->can_id = can_id; + cf->len = len; + if (!(can_flags & VIRTIO_CAN_FLAGS_RTR)) { + /* RTR frames have a DLC but no payload */ + memcpy(cf->data, can_rx->sdu, len); + } + + if (netif_receive_skb(skb) == NET_RX_SUCCESS) { + stats->rx_packets++; + if (!(can_flags & VIRTIO_CAN_FLAGS_RTR)) + stats->rx_bytes += len; + } + +putback: + /* Put processed RX buffer back into avail queue */ + ret = virtio_can_add_inbuf(vq, can_rx, + priv->rpkt_len); + if (!ret) + virtqueue_kick(vq); + return 1; /* Queue was not empty so there may be more data */ +} + +static int virtio_can_handle_busoff(struct net_device *dev) +{ + struct virtio_can_priv *priv = netdev_priv(dev); + struct can_frame *cf; + struct sk_buff *skb; + + if (!priv->busoff_pending) + return 0; + + if (priv->can.state < CAN_STATE_BUS_OFF) { + netdev_dbg(dev, "entered error bus off state\n"); + + /* bus-off state */ + priv->can.state = CAN_STATE_BUS_OFF; + priv->can.can_stats.bus_off++; + can_bus_off(dev); + } + + /* propagate the error condition to the CAN stack */ + skb = alloc_can_err_skb(dev, &cf); + if (unlikely(!skb)) + return 0; + + /* bus-off state */ + cf->can_id |= CAN_ERR_BUSOFF; + + /* Ensure that the BusOff indication does not get lost */ + if (netif_receive_skb(skb) == NET_RX_SUCCESS) + priv->busoff_pending = false; + + return 1; +} + +static int virtio_can_rx_poll(struct napi_struct *napi, int quota) +{ + struct net_device *dev = napi->dev; + struct virtio_can_priv *priv = netdev_priv(dev); + struct virtqueue *vq = priv->vqs[VIRTIO_CAN_QUEUE_RX]; + int work_done = 0; + + work_done += virtio_can_handle_busoff(dev); + + while (work_done < quota && virtio_can_read_rx_queue(vq) != 0) + work_done++; + + if (work_done < quota) + virtqueue_napi_complete(napi, vq, work_done); + + return work_done; +} + +static void virtio_can_rx_intr(struct virtqueue *vq) +{ + struct virtio_can_priv *can_priv = vq->vdev->priv; + + virtqueue_disable_cb(vq); + napi_schedule(&can_priv->napi); +} + +static void virtio_can_control_intr(struct virtqueue *vq) +{ + struct virtio_can_priv *can_priv = vq->vdev->priv; + + complete(&can_priv->ctrl_done); +} + +static void virtio_can_config_changed(struct virtio_device *vdev) +{ + struct virtio_can_priv *can_priv = vdev->priv; + u16 status; + + status = virtio_cread16(vdev, offsetof(struct virtio_can_config, + status)); + + if (!(status & VIRTIO_CAN_S_CTRL_BUSOFF)) + return; + + if (!can_priv->busoff_pending && + can_priv->can.state < CAN_STATE_BUS_OFF) { + can_priv->busoff_pending = true; + napi_schedule(&can_priv->napi); + } +} + +static void virtio_can_populate_rx_vq(struct virtio_device *vdev) +{ + struct virtio_can_priv *priv = vdev->priv; + struct virtqueue *vq = priv->vqs[VIRTIO_CAN_QUEUE_RX]; + unsigned int buf_size = priv->rpkt_len; + int num_elements = vq->num_free; + u8 *buf = (u8 *)priv->rpkt; + unsigned int idx; + int ret = 0; + + for (idx = 0; idx < num_elements; idx++) { + ret = virtio_can_add_inbuf(vq, buf, buf_size); + if (ret < 0) { + dev_dbg(&vdev->dev, "rpkt fill: ret=%d, idx=%u, size=%u\n", + ret, idx, buf_size); + break; + } + buf += buf_size; + } + + if (idx > 0) + virtqueue_kick(vq); + + dev_dbg(&vdev->dev, "%u rpkt added\n", idx); +} + +static int virtio_can_find_vqs(struct virtio_can_priv *priv) +{ + struct virtqueue_info vqs_info[] = { + { "can-tx", virtio_can_tx_intr }, + { "can-rx", virtio_can_rx_intr }, + { "can-state-ctrl", virtio_can_control_intr }, + }; + + /* Find the queues. */ + return virtio_find_vqs(priv->vdev, VIRTIO_CAN_QUEUE_COUNT, priv->vqs, + vqs_info, NULL); +} + +/* Function must not be called before virtio_can_find_vqs() has been run */ +static void virtio_can_del_vq(struct virtio_device *vdev) +{ + struct virtio_can_priv *priv = vdev->priv; + struct virtqueue *vq = priv->vqs[VIRTIO_CAN_QUEUE_TX]; + struct virtio_can_tx *can_tx_msg; + int q; + + if (!vq) + return; + + /* Reset the device */ + virtio_reset_device(vdev); + + /* From here we have dead silence from the device side so no locks + * are needed to protect against device side events. + */ + + /* Free pending TX buffers which were allocated in virtio_can_start_xmit() */ + while ((can_tx_msg = virtqueue_detach_unused_buf(vq))) { + can_free_echo_skb(priv->dev, can_tx_msg->putidx, NULL); + virtio_can_free_tx_idx(priv, can_tx_msg->putidx); + kfree(can_tx_msg); + } + + /* RX and control queue buffers are managed elsewhere, just detach */ + for (q = VIRTIO_CAN_QUEUE_RX; q < VIRTIO_CAN_QUEUE_COUNT; q++) + while (virtqueue_detach_unused_buf(priv->vqs[q])) + ; + + if (vdev->config->del_vqs) + vdev->config->del_vqs(vdev); + + memset(priv->vqs, 0, sizeof(priv->vqs)); +} + +static void virtio_can_remove(struct virtio_device *vdev) +{ + struct virtio_can_priv *priv = vdev->priv; + struct net_device *dev = priv->dev; + + unregister_candev(dev); + + virtio_can_del_vq(vdev); + + virtio_can_free_candev(dev); +} + +static int virtio_can_validate(struct virtio_device *vdev) +{ + /* CAN needs always access to the config space. + * Check that the driver can access the config space + */ + if (!vdev->config->get) { + dev_err(&vdev->dev, "%s failure: config access disabled\n", + __func__); + return -EINVAL; + } + + if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) { + dev_err(&vdev->dev, + "device does not comply with spec version 1.x\n"); + return -EINVAL; + } + + return 0; +} + +static int virtio_can_probe(struct virtio_device *vdev) +{ + struct virtio_can_priv *priv; + struct net_device *dev; + size_t size; + int err; + + dev = alloc_candev(sizeof(struct virtio_can_priv), + VIRTIO_CAN_ECHO_SKB_MAX); + if (!dev) + return -ENOMEM; + + priv = netdev_priv(dev); + + ida_init(&priv->tx_putidx_ida); + + netif_napi_add(dev, &priv->napi, virtio_can_rx_poll); + netif_napi_add(dev, &priv->napi_tx, virtio_can_tx_poll); + + SET_NETDEV_DEV(dev, &vdev->dev); + + priv->dev = dev; + priv->vdev = vdev; + vdev->priv = priv; + + priv->can.do_set_mode = virtio_can_set_mode; + priv->can.bittiming.bitrate = CAN_BITRATE_UNKNOWN; + /* Set Virtio CAN supported operations */ + priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING; + if (virtio_has_feature(vdev, VIRTIO_CAN_F_CAN_FD)) { + priv->can.fd.data_bittiming.bitrate = CAN_BITRATE_UNKNOWN; + err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD); + if (err != 0) + goto on_failure; + } + + /* Initialize virtqueues */ + err = virtio_can_find_vqs(priv); + if (err != 0) + goto on_failure; + + spin_lock_init(&priv->tx_lock); + mutex_init(&priv->ctrl_lock); + + init_completion(&priv->ctrl_done); + + priv->rpkt_len = sizeof(struct virtio_can_rx); + + if (virtio_has_feature(vdev, VIRTIO_CAN_F_CAN_FD)) + priv->rpkt_len += CANFD_MAX_DLEN; + else + priv->rpkt_len += CAN_MAX_DLEN; + + size = priv->rpkt_len * priv->vqs[VIRTIO_CAN_QUEUE_RX]->num_free; + priv->rpkt = devm_kzalloc(&vdev->dev, size, GFP_KERNEL); + if (!priv->rpkt) { + virtio_can_del_vq(vdev); + err = -ENOMEM; + goto on_failure; + } + virtio_can_populate_rx_vq(vdev); + + err = register_virtio_can_dev(dev); + if (err) { + virtio_can_del_vq(vdev); + goto on_failure; + } + + return 0; + +on_failure: + virtio_can_free_candev(dev); + return err; +} + +static int __maybe_unused virtio_can_freeze(struct virtio_device *vdev) +{ + struct virtio_can_priv *priv = vdev->priv; + struct net_device *ndev = priv->dev; + + if (netif_running(ndev)) { + /* virtio_can_close() calls netif_stop_queue(), virtio_can_stop(), + * napi_disable() and close_candev(). Call it directly (not via + * dev_close()) to preserve IFF_UP so that netif_running() returns + * true in virtio_can_restore() and the device is brought back up. + */ + virtio_can_close(ndev); + netif_device_detach(ndev); + } + + priv->can.state = CAN_STATE_SLEEPING; + + virtio_can_del_vq(vdev); + + return 0; +} + +static int __maybe_unused virtio_can_restore(struct virtio_device *vdev) +{ + struct virtio_can_priv *priv = vdev->priv; + struct net_device *ndev = priv->dev; + size_t size; + int err; + + err = virtio_can_find_vqs(priv); + if (err != 0) + return err; + + size = priv->rpkt_len * priv->vqs[VIRTIO_CAN_QUEUE_RX]->num_free; + priv->rpkt = devm_krealloc(&vdev->dev, priv->rpkt, size, GFP_KERNEL | __GFP_ZERO); + if (!priv->rpkt) { + virtio_can_del_vq(vdev); + return -ENOMEM; + } + virtio_can_populate_rx_vq(vdev); + + if (netif_running(ndev)) { + /* virtio_can_open() calls open_candev(), virtio_can_start(), + * napi_enable() and netif_start_queue(). Call it directly (not + * via dev_open()) since IFF_UP is still set from before freeze. + */ + err = virtio_can_open(ndev); + if (err) { + virtio_can_del_vq(vdev); + return err; + } + netif_device_attach(ndev); + } else { + priv->can.state = CAN_STATE_STOPPED; + } + + return 0; +} + +static struct virtio_device_id virtio_can_id_table[] = { + { VIRTIO_ID_CAN, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static unsigned int features[] = { + VIRTIO_CAN_F_CAN_CLASSIC, + VIRTIO_CAN_F_CAN_FD, + VIRTIO_CAN_F_LATE_TX_ACK, + VIRTIO_CAN_F_RTR_FRAMES, +}; + +static struct virtio_driver virtio_can_driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = virtio_can_id_table, + .validate = virtio_can_validate, + .probe = virtio_can_probe, + .remove = virtio_can_remove, + .config_changed = virtio_can_config_changed, +#ifdef CONFIG_PM_SLEEP + .freeze = virtio_can_freeze, + .restore = virtio_can_restore, +#endif +}; + +module_virtio_driver(virtio_can_driver); +MODULE_DEVICE_TABLE(virtio, virtio_can_id_table); + +MODULE_AUTHOR("OpenSynergy GmbH"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("CAN bus driver for Virtio CAN controller"); diff --git a/include/uapi/linux/virtio_can.h b/include/uapi/linux/virtio_can.h new file mode 100644 index 000000000000..08d7e3e78776 --- /dev/null +++ b/include/uapi/linux/virtio_can.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * Copyright (C) 2021-2023 OpenSynergy GmbH + * Copyright Red Hat, Inc. 2025 + */ +#ifndef _LINUX_VIRTIO_VIRTIO_CAN_H +#define _LINUX_VIRTIO_VIRTIO_CAN_H + +#include +#include +#include +#include + +/* Feature bit numbers */ +#define VIRTIO_CAN_F_CAN_CLASSIC 0 +#define VIRTIO_CAN_F_CAN_FD 1 +#define VIRTIO_CAN_F_RTR_FRAMES 2 +#define VIRTIO_CAN_F_LATE_TX_ACK 3 + +/* CAN Result Types */ +#define VIRTIO_CAN_RESULT_OK 0 +#define VIRTIO_CAN_RESULT_NOT_OK 1 + +/* CAN flags to determine type of CAN Id */ +#define VIRTIO_CAN_FLAGS_EXTENDED 0x8000 +#define VIRTIO_CAN_FLAGS_FD 0x4000 +#define VIRTIO_CAN_FLAGS_RTR 0x2000 + +#define VIRTIO_CAN_MAX_DLEN 64 // this is like CANFD_MAX_DLEN + +struct virtio_can_config { +#define VIRTIO_CAN_S_CTRL_BUSOFF (1u << 0) /* Controller BusOff */ + /* CAN controller status */ + __le16 status; +}; + +/* TX queue message types */ +struct virtio_can_tx_out { +#define VIRTIO_CAN_TX 0x0001 + __le16 msg_type; + __le16 length; /* 0..8 CC, 0..64 CAN-FD, 0..2048 CAN-XL, 12 bits */ + __u8 reserved_classic_dlc; /* If CAN classic length = 8 then DLC can be 8..15 */ + __u8 padding; + __le16 reserved_xl_priority; /* May be needed for CAN XL priority */ + __le32 flags; + __le32 can_id; + __u8 sdu[] __counted_by_le(length); +}; + +struct virtio_can_tx_in { + __u8 result; +}; + +/* RX queue message types */ +struct virtio_can_rx { +#define VIRTIO_CAN_RX 0x0101 + __le16 msg_type; + __le16 length; /* 0..8 CC, 0..64 CAN-FD, 0..2048 CAN-XL, 12 bits */ + __u8 reserved_classic_dlc; /* If CAN classic length = 8 then DLC can be 8..15 */ + __u8 padding; + __le16 reserved_xl_priority; /* May be needed for CAN XL priority */ + __le32 flags; + __le32 can_id; + __u8 sdu[] __counted_by_le(length); +}; + +/* Control queue message types */ +struct virtio_can_control_out { +#define VIRTIO_CAN_SET_CTRL_MODE_START 0x0201 +#define VIRTIO_CAN_SET_CTRL_MODE_STOP 0x0202 + __le16 msg_type; +}; + +struct virtio_can_control_in { + __u8 result; +}; + +#endif /* #ifndef _LINUX_VIRTIO_VIRTIO_CAN_H */ -- cgit v1.3-14-g43fede From 8cb2c9285e4ce9154f45fb15633ebd45dfd8d9cf Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 4 Jun 2026 15:57:15 -0700 Subject: can: virtio: Fix comment in UAPI header When compile testing the UAPI headers with clang, there is an warning turned error for using a C++ style ('//') comment, which is explicitly forbidden for UAPI headers. In file included from :1: ./usr/include/linux/virtio_can.h:29:35: error: // comments are not allowed in this language [-Werror,-Wcomment] 29 | #define VIRTIO_CAN_MAX_DLEN 64 // this is like CANFD_MAX_DLEN | ^ 1 error generated. Switch to a standard C style comment. Fixes: 2b6b4bb7d96f ("can: virtio: Add virtio CAN driver") Signed-off-by: Nathan Chancellor Signed-off-by: Michael S. Tsirkin Message-ID: <20260604-virtio_can-fix-uapi-comment-v1-1-199fa96ec5f0@kernel.org> --- include/uapi/linux/virtio_can.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_can.h b/include/uapi/linux/virtio_can.h index 08d7e3e78776..e054d5099241 100644 --- a/include/uapi/linux/virtio_can.h +++ b/include/uapi/linux/virtio_can.h @@ -26,7 +26,7 @@ #define VIRTIO_CAN_FLAGS_FD 0x4000 #define VIRTIO_CAN_FLAGS_RTR 0x2000 -#define VIRTIO_CAN_MAX_DLEN 64 // this is like CANFD_MAX_DLEN +#define VIRTIO_CAN_MAX_DLEN 64 /* this is like CANFD_MAX_DLEN */ struct virtio_can_config { #define VIRTIO_CAN_S_CTRL_BUSOFF (1u << 0) /* Controller BusOff */ -- cgit v1.3-14-g43fede From 32b0b8953343eaceaa816a9ead3b6bb66355c64e Mon Sep 17 00:00:00 2001 From: Louis Scalbert Date: Wed, 3 Jun 2026 17:03:28 +0200 Subject: bonding: 3ad: add lacp_strict configuration knob When an 802.3ad (LACP) bonding interface has no slaves in the collecting/distributing state, the bonding master still reports carrier as up as long as at least 'min_links' slaves have carrier. In this situation, only one slave is effectively used for TX/RX, while traffic received on other slaves is dropped. Upper-layer daemons therefore consider the interface operational, even though traffic may be blackholed if the lack of LACP negotiation means the partner is not ready to deal with traffic. Introduce a configuration knob to control this behavior. It allows the bonding master to assert carrier only when at least 'min_links' slaves are in Collecting_Distributing state. The default mode preserves the existing behavior. This patch only introduces the knob; its behavior is implemented in the subsequent commit. Fixes: 655f8919d549 ("bonding: add min links parameter to 802.3ad") Signed-off-by: Louis Scalbert Acked-by: Jay Vosburgh Link: https://patch.msgid.link/20260603150331.1919611-4-louis.scalbert@6wind.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/rt-link.yaml | 3 +++ Documentation/networking/bonding.rst | 23 +++++++++++++++++++++++ drivers/net/bonding/bond_main.c | 1 + drivers/net/bonding/bond_netlink.c | 16 ++++++++++++++++ drivers/net/bonding/bond_options.c | 26 ++++++++++++++++++++++++++ include/net/bond_options.h | 1 + include/net/bonding.h | 1 + include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/if_link.h | 1 + 9 files changed, 73 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index 694fd0a3a0c1..892979da098e 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -1356,6 +1356,9 @@ attribute-sets: - name: broadcast-neigh type: u8 + - + name: lacp-strict + type: u8 - name: bond-ad-info-attrs name-prefix: ifla-bond-ad-info- diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index e700bf1d095c..33ca5afafdf6 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -619,6 +619,29 @@ min_links aggregator cannot be active without at least one available link, setting this option to 0 or to 1 has the exact same effect. +lacp_strict + + Specifies the fallback behavior of a bonding when LACP negotiation + fails on all slave links, i.e. when no slave is in the + Collecting_Distributing state, while at least `min_links` link still + reports carrier up. + + This option is only applicable to 802.3ad mode (mode 4). + + Valid values are: + + off or 0 + One interface of the bond is selected to be active, in order to + facilitate communication with peer devices that do not implement + LACP. + + on or 1 + Interfaces are only permitted to be made active if they have an + active LACP partner and have successfully reached + Collecting_Distributing state. + + The default value is 0 (off). + mode Specifies one of the bonding policies. The default is diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index be50125f0635..e044fc733b8c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -6457,6 +6457,7 @@ static int __init bond_check_params(struct bond_params *params) params->ad_user_port_key = ad_user_port_key; params->coupled_control = 1; params->broadcast_neighbor = 0; + params->lacp_strict = 0; if (packets_per_slave > 0) { params->reciprocal_packets_per_slave = reciprocal_value(packets_per_slave); diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 90365d3f7ebf..4a11572f663d 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -143,6 +143,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED }, [IFLA_BOND_COUPLED_CONTROL] = { .type = NLA_U8 }, [IFLA_BOND_BROADCAST_NEIGH] = { .type = NLA_U8 }, + [IFLA_BOND_LACP_STRICT] = { .type = NLA_U8 }, }; static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { @@ -599,6 +600,16 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], return err; } + if (data[IFLA_BOND_LACP_STRICT]) { + int fallback_mode = nla_get_u8(data[IFLA_BOND_LACP_STRICT]); + + bond_opt_initval(&newval, fallback_mode); + err = __bond_opt_set(bond, BOND_OPT_LACP_STRICT, &newval, + data[IFLA_BOND_LACP_STRICT], extack); + if (err) + return err; + } + return 0; } @@ -671,6 +682,7 @@ static size_t bond_get_size(const struct net_device *bond_dev) nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS + nla_total_size(sizeof(u8)) + /* IFLA_BOND_COUPLED_CONTROL */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_BROADCAST_NEIGH */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_LACP_STRICT */ 0; } @@ -838,6 +850,10 @@ static int bond_fill_info(struct sk_buff *skb, bond->params.broadcast_neighbor)) goto nla_put_failure; + if (nla_put_u8(skb, IFLA_BOND_LACP_STRICT, + bond->params.lacp_strict)) + goto nla_put_failure; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info info; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 5095ac3dad2c..f01b3baa57b4 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -68,6 +68,8 @@ static int bond_option_lacp_active_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_lacp_rate_set(struct bonding *bond, const struct bond_opt_value *newval); +static int bond_option_lacp_strict_set(struct bonding *bond, + const struct bond_opt_value *newval); static int bond_option_ad_select_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_queue_id_set(struct bonding *bond, @@ -162,6 +164,12 @@ static const struct bond_opt_value bond_lacp_rate_tbl[] = { { NULL, -1, 0}, }; +static const struct bond_opt_value bond_lacp_strict_tbl[] = { + { "off", 0, BOND_VALFLAG_DEFAULT}, + { "on", 1, 0}, + { NULL, -1, 0 } +}; + static const struct bond_opt_value bond_ad_select_tbl[] = { { "stable", BOND_AD_STABLE, BOND_VALFLAG_DEFAULT}, { "bandwidth", BOND_AD_BANDWIDTH, 0}, @@ -363,6 +371,14 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .values = bond_lacp_rate_tbl, .set = bond_option_lacp_rate_set }, + [BOND_OPT_LACP_STRICT] = { + .id = BOND_OPT_LACP_STRICT, + .name = "lacp_strict", + .desc = "Define the LACP fallback mode when no slaves have negotiated", + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)), + .values = bond_lacp_strict_tbl, + .set = bond_option_lacp_strict_set + }, [BOND_OPT_MINLINKS] = { .id = BOND_OPT_MINLINKS, .name = "min_links", @@ -1685,6 +1701,16 @@ static int bond_option_lacp_rate_set(struct bonding *bond, return 0; } +static int bond_option_lacp_strict_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + netdev_dbg(bond->dev, "Setting LACP fallback to %s (%llu)\n", + newval->string, newval->value); + bond->params.lacp_strict = newval->value; + + return 0; +} + static int bond_option_ad_select_set(struct bonding *bond, const struct bond_opt_value *newval) { diff --git a/include/net/bond_options.h b/include/net/bond_options.h index e6eedf23aea1..52b966e92793 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -79,6 +79,7 @@ enum { BOND_OPT_COUPLED_CONTROL, BOND_OPT_BROADCAST_NEIGH, BOND_OPT_ACTOR_PORT_PRIO, + BOND_OPT_LACP_STRICT, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index edd1942dcd73..2c54a36a8477 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -129,6 +129,7 @@ struct bond_params { int peer_notif_delay; int lacp_active; int lacp_fast; + int lacp_strict; unsigned int min_links; int ad_select; char primary[IFNAMSIZ]; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 363526549a01..43cecca49f01 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1603,6 +1603,7 @@ enum { IFLA_BOND_NS_IP6_TARGET, IFLA_BOND_COUPLED_CONTROL, IFLA_BOND_BROADCAST_NEIGH, + IFLA_BOND_LACP_STRICT, __IFLA_BOND_MAX, }; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 97a2d4411534..757ce5e9426e 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -1527,6 +1527,7 @@ enum { IFLA_BOND_NS_IP6_TARGET, IFLA_BOND_COUPLED_CONTROL, IFLA_BOND_BROADCAST_NEIGH, + IFLA_BOND_LACP_STRICT, __IFLA_BOND_MAX, }; -- cgit v1.3-14-g43fede From e98a9c61721c14bcd29f11f4802e52e908701f7a Mon Sep 17 00:00:00 2001 From: Tarun Sahu Date: Thu, 11 Jun 2026 09:30:40 +0000 Subject: liveupdate: Document that retrieve failure is permanent Signed-off-by: Tarun Sahu Reviewed-by: Pratyush Yadav (Google) Link: https://patch.msgid.link/faec5df2a3e90240cde5897bae2250cd7d44aeac.1781170056.git.tarunsahu@google.com Signed-off-by: Mike Rapoport (Microsoft) --- include/uapi/linux/liveupdate.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/liveupdate.h b/include/uapi/linux/liveupdate.h index 3a9ff53b02e0..4043d4038712 100644 --- a/include/uapi/linux/liveupdate.h +++ b/include/uapi/linux/liveupdate.h @@ -169,7 +169,9 @@ struct liveupdate_session_preserve_fd { * associated with the token and populates the @fd field with a new file * descriptor referencing the restored resource in the current (new) kernel. * This operation must be performed *before* signaling completion via - * %LIVEUPDATE_IOCTL_FINISH. + * %LIVEUPDATE_IOCTL_FINISH. If a retrieve of a token fails, subsequent + * attempts to retrieve the token fail with the same error code. Failed + * retrieves are not retried. * * Return: 0 on success, negative error code on failure (e.g., invalid token). */ -- cgit v1.3-14-g43fede From 13655144ddcad532c4e9338788041654a54e5c2f Mon Sep 17 00:00:00 2001 From: Fidelio Lawson Date: Tue, 9 Jun 2026 18:19:56 +0200 Subject: net: ethtool: add KSZ87xx low-loss cable PHY tunables Introduce vendor-specific PHY tunable identifiers to control the KSZ87xx low-loss cable erratum handling through the ethtool PHY tunable interface. The following tunables are added: - a boolean "short-cable" tunable, applying a documented and conservative preset intended for short or low-loss Ethernet cables; - an integer LPF bandwidth tunable, allowing advanced adjustment of the receiver low-pass filter bandwidth; - an integer DSP EQ initial value tunable, allowing advanced tuning of the PHY equalizer initialization. The actual behavior is implemented by the corresponding PHY and switch drivers. Reviewed-by: Marek Vasut Reviewed-by: Nicolai Buchwitz Signed-off-by: Fidelio Lawson Link: https://patch.msgid.link/20260609-ksz87xx_errata_low_loss_connections-v10-2-9ba4418cf3db@exotec.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 3 +++ net/ethtool/common.c | 3 +++ net/ethtool/ioctl.c | 7 +++++++ 3 files changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 1cdfb8341df2..a2091d4e00f3 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -291,6 +291,9 @@ enum phy_tunable_id { ETHTOOL_PHY_DOWNSHIFT, ETHTOOL_PHY_FAST_LINK_DOWN, ETHTOOL_PHY_EDPD, + ETHTOOL_PHY_SHORT_CABLE_PRESET, + ETHTOOL_PHY_LPF_BW, + ETHTOOL_PHY_DSP_EQ_INIT_VALUE, /* * Add your fresh new phy tunable attribute above and remember to update * phy_tunable_strings[] in net/ethtool/common.c diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 84ec88dee05c..a24d3a8a9ec1 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -101,6 +101,9 @@ phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN] = { [ETHTOOL_PHY_DOWNSHIFT] = "phy-downshift", [ETHTOOL_PHY_FAST_LINK_DOWN] = "phy-fast-link-down", [ETHTOOL_PHY_EDPD] = "phy-energy-detect-power-down", + [ETHTOOL_PHY_SHORT_CABLE_PRESET] = "phy-short-cable-preset", + [ETHTOOL_PHY_LPF_BW] = "phy-lpf-bandwidth", + [ETHTOOL_PHY_DSP_EQ_INIT_VALUE] = "phy-dsp-eq-init-value", }; #define __LINK_MODE_NAME(speed, type, duplex) \ diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index a7bff829b758..4b0bc503f930 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -3133,6 +3133,7 @@ static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna) switch (tuna->id) { case ETHTOOL_PHY_DOWNSHIFT: case ETHTOOL_PHY_FAST_LINK_DOWN: + case ETHTOOL_PHY_SHORT_CABLE_PRESET: if (tuna->len != sizeof(u8) || tuna->type_id != ETHTOOL_TUNABLE_U8) return -EINVAL; @@ -3142,6 +3143,12 @@ static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna) tuna->type_id != ETHTOOL_TUNABLE_U16) return -EINVAL; break; + case ETHTOOL_PHY_LPF_BW: + case ETHTOOL_PHY_DSP_EQ_INIT_VALUE: + if (tuna->len != sizeof(u32) || + tuna->type_id != ETHTOOL_TUNABLE_U32) + return -EINVAL; + break; default: return -EINVAL; } -- cgit v1.3-14-g43fede From 298ab7e6f1637cec44163f52e84e2030ec16ed9d Mon Sep 17 00:00:00 2001 From: Alex Mastro Date: Wed, 10 Jun 2026 13:44:41 -0700 Subject: iommufd: Clarify IOAS_MAP_FILE dma-buf support IOMMU_IOAS_MAP_FILE is documented as mapping a memfd, but the implementation first tries to resolve the fd as a dma-buf and has a special path for supported dma-buf exporters. In particular, VFIO PCI dma-bufs exported through VFIO_DEVICE_FEATURE_DMA_BUF can be mapped when they describe a single DMA range. Update the UAPI comment so userspace understands that certain kinds of dma-buf are supported in addition to memfd. Fixes: 44ebaa1744fd ("iommufd: Accept a DMABUF through IOMMU_IOAS_MAP_FILE") Link: https://patch.msgid.link/r/20260610-tmp-v1-1-b8ccbf557391@fb.com Signed-off-by: Alex Mastro Assisted-by: Codex:gpt-5.5-high Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index e998dfbd6960..0425d452d41e 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -224,13 +224,17 @@ struct iommu_ioas_map { * @size: sizeof(struct iommu_ioas_map_file) * @flags: same as for iommu_ioas_map * @ioas_id: same as for iommu_ioas_map - * @fd: the memfd to map - * @start: byte offset from start of file to map from + * @fd: the memfd or supported dma-buf file to map + * @start: byte offset from start of the file to map from * @length: same as for iommu_ioas_map * @iova: same as for iommu_ioas_map * - * Set an IOVA mapping from a memfd file. All other arguments and semantics - * match those of IOMMU_IOAS_MAP. + * Set an IOVA mapping from a memfd file. On kernels with dma-buf support, + * supported dma-buf files may also be accepted. This is not a generic + * dma-buf import path; currently supported dma-bufs include single-range + * VFIO PCI dma-bufs exported through VFIO_DEVICE_FEATURE_DMA_BUF, and + * other dma-bufs may be rejected. All other arguments and semantics match + * those of IOMMU_IOAS_MAP. */ struct iommu_ioas_map_file { __u32 size; -- cgit v1.3-14-g43fede From cdae65fc43f28b6508d85fa242264f3bc5c9a5c7 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Thu, 11 Jun 2026 12:21:33 +0200 Subject: tls: remove tls_toe and the related driver The tls_toe feature and its single user (chelsio chtls) have been unmaintained for multiple years. It also hooks into the core of the TCP implementation, and bypasses most of the networking stack. Signed-off-by: Sabrina Dubroca Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/1f30e73275c07bf879f547589872d0916025a52e.1781165969.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski --- Documentation/networking/tls-offload.rst | 7 +- arch/s390/configs/debug_defconfig | 1 - arch/s390/configs/defconfig | 1 - drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 3 +- drivers/net/ethernet/chelsio/inline_crypto/Kconfig | 12 - .../net/ethernet/chelsio/inline_crypto/Makefile | 1 - .../ethernet/chelsio/inline_crypto/chtls/Makefile | 6 - .../ethernet/chelsio/inline_crypto/chtls/chtls.h | 584 ----- .../chelsio/inline_crypto/chtls/chtls_cm.c | 2336 -------------------- .../chelsio/inline_crypto/chtls/chtls_cm.h | 218 -- .../chelsio/inline_crypto/chtls/chtls_hw.c | 462 ---- .../chelsio/inline_crypto/chtls/chtls_io.c | 1836 --------------- .../chelsio/inline_crypto/chtls/chtls_main.c | 642 ------ include/linux/netdev_features.h | 3 +- include/net/tls.h | 1 - include/net/tls_toe.h | 77 - include/uapi/linux/tls.h | 2 +- net/ethtool/common.c | 1 - net/tls/Kconfig | 10 - net/tls/Makefile | 1 - net/tls/tls_main.c | 17 - net/tls/tls_toe.c | 141 -- 22 files changed, 4 insertions(+), 6358 deletions(-) delete mode 100644 drivers/net/ethernet/chelsio/inline_crypto/chtls/Makefile delete mode 100644 drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h delete mode 100644 drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c delete mode 100644 drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h delete mode 100644 drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c delete mode 100644 drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c delete mode 100644 drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c delete mode 100644 include/net/tls_toe.h delete mode 100644 net/tls/tls_toe.c (limited to 'include/uapi/linux') diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst index c173f537bf4d..25ee8d9f12c9 100644 --- a/Documentation/networking/tls-offload.rst +++ b/Documentation/networking/tls-offload.rst @@ -13,7 +13,7 @@ Layer Protocol (ULP) and install the cryptographic connection state. For details regarding the user-facing interface refer to the TLS documentation in :ref:`Documentation/networking/tls.rst `. -``ktls`` can operate in three modes: +``ktls`` can operate in two modes: * Software crypto mode (``TLS_SW``) - CPU handles the cryptography. In most basic cases only crypto operations synchronous with the CPU @@ -26,11 +26,6 @@ documentation in :ref:`Documentation/networking/tls.rst `. This mode integrates best with the kernel stack and is described in detail in the remaining part of this document (``ethtool`` flags ``tls-hw-tx-offload`` and ``tls-hw-rx-offload``). - * Full TCP NIC offload mode (``TLS_HW_RECORD``) - mode of operation where - NIC driver and firmware replace the kernel networking stack - with its own TCP handling, it is not usable in production environments - making use of the Linux networking stack for example any firewalling - abilities or QoS and packet scheduling (``ethtool`` flag ``tls-hw-record``). The operation mode is selected automatically based on device configuration, offload opt-in or opt-out on per-connection basis is not currently supported. diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 471d078e5c53..54637be87fb7 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -125,7 +125,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_TLS_DEVICE=y -CONFIG_TLS_TOE=y CONFIG_XFRM_USER=m CONFIG_NET_KEY=m CONFIG_SMC=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index c0d39d05f50a..5f5114a253cf 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -116,7 +116,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_TLS_DEVICE=y -CONFIG_TLS_TOE=y CONFIG_XFRM_USER=m CONFIG_NET_KEY=m CONFIG_SMC=m diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 6df98fca932f..9e2c2fa16d7a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6795,8 +6795,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_TSO | NETIF_F_TSO6; netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_HW_TLS_RECORD; + NETIF_F_GSO_UDP_TUNNEL_CSUM; if (adapter->rawf_cnt) netdev->udp_tunnel_nic_info = &cxgb_udp_tunnels; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/Kconfig b/drivers/net/ethernet/chelsio/inline_crypto/Kconfig index 521955e1f894..b7d452f4a7f1 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/Kconfig +++ b/drivers/net/ethernet/chelsio/inline_crypto/Kconfig @@ -13,18 +13,6 @@ config CHELSIO_INLINE_CRYPTO if CHELSIO_INLINE_CRYPTO -config CRYPTO_DEV_CHELSIO_TLS - tristate "Chelsio Crypto Inline TLS Driver" - depends on CHELSIO_T4 - depends on TLS - depends on TLS_TOE - help - Support Chelsio Inline TLS with Chelsio crypto accelerator. - Enable inline TLS support for Tx and Rx. - - To compile this driver as a module, choose M here: the module - will be called chtls. - config CHELSIO_IPSEC_INLINE tristate "Chelsio IPSec XFRM Tx crypto offload" depends on CHELSIO_T4 diff --git a/drivers/net/ethernet/chelsio/inline_crypto/Makefile b/drivers/net/ethernet/chelsio/inline_crypto/Makefile index 27e6d7e2f1eb..ca6548adc6a7 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/Makefile +++ b/drivers/net/ethernet/chelsio/inline_crypto/Makefile @@ -1,4 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_CRYPTO_DEV_CHELSIO_TLS) += chtls/ obj-$(CONFIG_CHELSIO_IPSEC_INLINE) += ch_ipsec/ obj-$(CONFIG_CHELSIO_TLS_DEVICE) += ch_ktls/ diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/Makefile b/drivers/net/ethernet/chelsio/inline_crypto/chtls/Makefile deleted file mode 100644 index bc11495acdb3..000000000000 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/Makefile +++ /dev/null @@ -1,6 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -ccflags-y := -I $(srctree)/drivers/net/ethernet/chelsio/cxgb4 \ - -I $(srctree)/drivers/crypto/chelsio - -obj-$(CONFIG_CRYPTO_DEV_CHELSIO_TLS) += chtls.o -chtls-objs := chtls_main.o chtls_cm.o chtls_io.o chtls_hw.o diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h deleted file mode 100644 index 1de5744a49b0..000000000000 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h +++ /dev/null @@ -1,584 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (c) 2018 Chelsio Communications, Inc. - */ - -#ifndef __CHTLS_H__ -#define __CHTLS_H__ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "t4fw_api.h" -#include "t4_msg.h" -#include "cxgb4.h" -#include "cxgb4_uld.h" -#include "l2t.h" -#include "chcr_algo.h" -#include "chcr_core.h" -#include "chcr_crypto.h" - -#define CHTLS_DRV_VERSION "1.0.0.0-ko" - -#define TLS_KEYCTX_RXFLIT_CNT_S 24 -#define TLS_KEYCTX_RXFLIT_CNT_V(x) ((x) << TLS_KEYCTX_RXFLIT_CNT_S) - -#define TLS_KEYCTX_RXPROT_VER_S 20 -#define TLS_KEYCTX_RXPROT_VER_M 0xf -#define TLS_KEYCTX_RXPROT_VER_V(x) ((x) << TLS_KEYCTX_RXPROT_VER_S) - -#define TLS_KEYCTX_RXCIPH_MODE_S 16 -#define TLS_KEYCTX_RXCIPH_MODE_M 0xf -#define TLS_KEYCTX_RXCIPH_MODE_V(x) ((x) << TLS_KEYCTX_RXCIPH_MODE_S) - -#define TLS_KEYCTX_RXAUTH_MODE_S 12 -#define TLS_KEYCTX_RXAUTH_MODE_M 0xf -#define TLS_KEYCTX_RXAUTH_MODE_V(x) ((x) << TLS_KEYCTX_RXAUTH_MODE_S) - -#define TLS_KEYCTX_RXCIAU_CTRL_S 11 -#define TLS_KEYCTX_RXCIAU_CTRL_V(x) ((x) << TLS_KEYCTX_RXCIAU_CTRL_S) - -#define TLS_KEYCTX_RX_SEQCTR_S 9 -#define TLS_KEYCTX_RX_SEQCTR_M 0x3 -#define TLS_KEYCTX_RX_SEQCTR_V(x) ((x) << TLS_KEYCTX_RX_SEQCTR_S) - -#define TLS_KEYCTX_RX_VALID_S 8 -#define TLS_KEYCTX_RX_VALID_V(x) ((x) << TLS_KEYCTX_RX_VALID_S) - -#define TLS_KEYCTX_RXCK_SIZE_S 3 -#define TLS_KEYCTX_RXCK_SIZE_M 0x7 -#define TLS_KEYCTX_RXCK_SIZE_V(x) ((x) << TLS_KEYCTX_RXCK_SIZE_S) - -#define TLS_KEYCTX_RXMK_SIZE_S 0 -#define TLS_KEYCTX_RXMK_SIZE_M 0x7 -#define TLS_KEYCTX_RXMK_SIZE_V(x) ((x) << TLS_KEYCTX_RXMK_SIZE_S) - -#define KEYCTX_TX_WR_IV_S 55 -#define KEYCTX_TX_WR_IV_M 0x1ffULL -#define KEYCTX_TX_WR_IV_V(x) ((x) << KEYCTX_TX_WR_IV_S) -#define KEYCTX_TX_WR_IV_G(x) \ - (((x) >> KEYCTX_TX_WR_IV_S) & KEYCTX_TX_WR_IV_M) - -#define KEYCTX_TX_WR_AAD_S 47 -#define KEYCTX_TX_WR_AAD_M 0xffULL -#define KEYCTX_TX_WR_AAD_V(x) ((x) << KEYCTX_TX_WR_AAD_S) -#define KEYCTX_TX_WR_AAD_G(x) (((x) >> KEYCTX_TX_WR_AAD_S) & \ - KEYCTX_TX_WR_AAD_M) - -#define KEYCTX_TX_WR_AADST_S 39 -#define KEYCTX_TX_WR_AADST_M 0xffULL -#define KEYCTX_TX_WR_AADST_V(x) ((x) << KEYCTX_TX_WR_AADST_S) -#define KEYCTX_TX_WR_AADST_G(x) \ - (((x) >> KEYCTX_TX_WR_AADST_S) & KEYCTX_TX_WR_AADST_M) - -#define KEYCTX_TX_WR_CIPHER_S 30 -#define KEYCTX_TX_WR_CIPHER_M 0x1ffULL -#define KEYCTX_TX_WR_CIPHER_V(x) ((x) << KEYCTX_TX_WR_CIPHER_S) -#define KEYCTX_TX_WR_CIPHER_G(x) \ - (((x) >> KEYCTX_TX_WR_CIPHER_S) & KEYCTX_TX_WR_CIPHER_M) - -#define KEYCTX_TX_WR_CIPHERST_S 23 -#define KEYCTX_TX_WR_CIPHERST_M 0x7f -#define KEYCTX_TX_WR_CIPHERST_V(x) ((x) << KEYCTX_TX_WR_CIPHERST_S) -#define KEYCTX_TX_WR_CIPHERST_G(x) \ - (((x) >> KEYCTX_TX_WR_CIPHERST_S) & KEYCTX_TX_WR_CIPHERST_M) - -#define KEYCTX_TX_WR_AUTH_S 14 -#define KEYCTX_TX_WR_AUTH_M 0x1ff -#define KEYCTX_TX_WR_AUTH_V(x) ((x) << KEYCTX_TX_WR_AUTH_S) -#define KEYCTX_TX_WR_AUTH_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTH_S) & KEYCTX_TX_WR_AUTH_M) - -#define KEYCTX_TX_WR_AUTHST_S 7 -#define KEYCTX_TX_WR_AUTHST_M 0x7f -#define KEYCTX_TX_WR_AUTHST_V(x) ((x) << KEYCTX_TX_WR_AUTHST_S) -#define KEYCTX_TX_WR_AUTHST_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTHST_S) & KEYCTX_TX_WR_AUTHST_M) - -#define KEYCTX_TX_WR_AUTHIN_S 0 -#define KEYCTX_TX_WR_AUTHIN_M 0x7f -#define KEYCTX_TX_WR_AUTHIN_V(x) ((x) << KEYCTX_TX_WR_AUTHIN_S) -#define KEYCTX_TX_WR_AUTHIN_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTHIN_S) & KEYCTX_TX_WR_AUTHIN_M) - -struct sge_opaque_hdr { - void *dev; - dma_addr_t addr[MAX_SKB_FRAGS + 1]; -}; - -#define MAX_IVS_PAGE 256 -#define TLS_KEY_CONTEXT_SZ 64 -#define CIPHER_BLOCK_SIZE 16 -#define GCM_TAG_SIZE 16 -#define KEY_ON_MEM_SZ 16 -#define AEAD_EXPLICIT_DATA_SIZE 8 -#define TLS_HEADER_LENGTH 5 -#define SCMD_CIPH_MODE_AES_GCM 2 -/* Any MFS size should work and come from openssl */ -#define TLS_MFS 16384 - -#define RSS_HDR sizeof(struct rss_header) -#define TLS_WR_CPL_LEN \ - (sizeof(struct fw_tlstx_data_wr) + sizeof(struct cpl_tx_tls_sfo)) - -enum { - CHTLS_KEY_CONTEXT_DSGL, - CHTLS_KEY_CONTEXT_IMM, - CHTLS_KEY_CONTEXT_DDR, -}; - -enum { - CHTLS_LISTEN_START, - CHTLS_LISTEN_STOP, -}; - -/* Flags for return value of CPL message handlers */ -enum { - CPL_RET_BUF_DONE = 1, /* buffer processing done */ - CPL_RET_BAD_MSG = 2, /* bad CPL message */ - CPL_RET_UNKNOWN_TID = 4 /* unexpected unknown TID */ -}; - -#define LISTEN_INFO_HASH_SIZE 32 -#define RSPQ_HASH_BITS 5 -struct listen_info { - struct listen_info *next; /* Link to next entry */ - struct sock *sk; /* The listening socket */ - unsigned int stid; /* The server TID */ -}; - -enum { - T4_LISTEN_START_PENDING, - T4_LISTEN_STARTED -}; - -enum csk_flags { - CSK_CALLBACKS_CHKD, /* socket callbacks have been sanitized */ - CSK_ABORT_REQ_RCVD, /* received one ABORT_REQ_RSS message */ - CSK_TX_MORE_DATA, /* sending ULP data; don't set SHOVE bit */ - CSK_TX_WAIT_IDLE, /* suspend Tx until in-flight data is ACKed */ - CSK_ABORT_SHUTDOWN, /* shouldn't send more abort requests */ - CSK_ABORT_RPL_PENDING, /* expecting an abort reply */ - CSK_CLOSE_CON_REQUESTED,/* we've sent a close_conn_req */ - CSK_TX_DATA_SENT, /* sent a TX_DATA WR on this connection */ - CSK_TX_FAILOVER, /* Tx traffic failing over */ - CSK_UPDATE_RCV_WND, /* Need to update rcv window */ - CSK_RST_ABORTED, /* outgoing RST was aborted */ - CSK_TLS_HANDSHK, /* TLS Handshake */ - CSK_CONN_INLINE, /* Connection on HW */ -}; - -enum chtls_cdev_state { - CHTLS_CDEV_STATE_UP = 1 -}; - -struct listen_ctx { - struct sock *lsk; - struct chtls_dev *cdev; - struct sk_buff_head synq; - u32 state; -}; - -struct key_map { - unsigned long *addr; - unsigned int start; - unsigned int available; - unsigned int size; - spinlock_t lock; /* lock for key id request from map */ -} __packed; - -struct tls_scmd { - u32 seqno_numivs; - u32 ivgen_hdrlen; -}; - -struct chtls_dev { - struct tls_toe_device tlsdev; - struct list_head list; - struct cxgb4_lld_info *lldi; - struct pci_dev *pdev; - struct listen_info *listen_hash_tab[LISTEN_INFO_HASH_SIZE]; - spinlock_t listen_lock; /* lock for listen list */ - struct net_device **ports; - struct tid_info *tids; - unsigned int pfvf; - const unsigned short *mtus; - - struct idr hwtid_idr; - struct idr stid_idr; - - spinlock_t idr_lock ____cacheline_aligned_in_smp; - - struct net_device *egr_dev[NCHAN * 2]; - struct sk_buff *rspq_skb_cache[1 << RSPQ_HASH_BITS]; - struct sk_buff *askb; - - struct sk_buff_head deferq; - struct work_struct deferq_task; - - struct list_head list_node; - struct list_head rcu_node; - struct list_head na_node; - unsigned int send_page_order; - int max_host_sndbuf; - u32 round_robin_cnt; - struct key_map kmap; - unsigned int cdev_state; -}; - -struct chtls_listen { - struct chtls_dev *cdev; - struct sock *sk; -}; - -struct chtls_hws { - struct sk_buff_head sk_recv_queue; - u8 txqid; - u8 ofld; - u16 type; - u16 rstate; - u16 keyrpl; - u16 pldlen; - u16 rcvpld; - u16 compute; - u16 expansion; - u16 keylen; - u16 pdus; - u16 adjustlen; - u16 ivsize; - u16 txleft; - u32 mfs; - s32 txkey; - s32 rxkey; - u32 fcplenmax; - u32 copied_seq; - u64 tx_seq_no; - struct tls_scmd scmd; - union { - struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; - struct tls12_crypto_info_aes_gcm_256 aes_gcm_256; - } crypto_info; -}; - -struct chtls_sock { - struct sock *sk; - struct chtls_dev *cdev; - struct l2t_entry *l2t_entry; /* pointer to the L2T entry */ - struct net_device *egress_dev; /* TX_CHAN for act open retry */ - - struct sk_buff_head txq; - struct sk_buff *wr_skb_head; - struct sk_buff *wr_skb_tail; - struct sk_buff *ctrl_skb_cache; - struct sk_buff *txdata_skb_cache; /* abort path messages */ - struct kref kref; - unsigned long flags; - u32 opt2; - u32 wr_credits; - u32 wr_unacked; - u32 wr_max_credits; - u32 wr_nondata; - u32 hwtid; /* TCP Control Block ID */ - u32 txq_idx; - u32 rss_qid; - u32 tid; - u32 idr; - u32 mss; - u32 ulp_mode; - u32 tx_chan; - u32 rx_chan; - u32 sndbuf; - u32 txplen_max; - u32 mtu_idx; /* MTU table index */ - u32 smac_idx; - u8 port_id; - u8 tos; - u16 resv2; - u32 delack_mode; - u32 delack_seq; - u32 snd_win; - u32 rcv_win; - - void *passive_reap_next; /* placeholder for passive */ - struct chtls_hws tlshws; - struct synq { - struct sk_buff *next; - struct sk_buff *prev; - } synq; - struct listen_ctx *listen_ctx; -}; - -struct tls_hdr { - u8 type; - u16 version; - u16 length; -} __packed; - -struct tlsrx_cmp_hdr { - u8 type; - u16 version; - u16 length; - - u64 tls_seq; - u16 reserved1; - u8 res_to_mac_error; -} __packed; - -/* res_to_mac_error fields */ -#define TLSRX_HDR_PKT_INT_ERROR_S 4 -#define TLSRX_HDR_PKT_INT_ERROR_M 0x1 -#define TLSRX_HDR_PKT_INT_ERROR_V(x) \ - ((x) << TLSRX_HDR_PKT_INT_ERROR_S) -#define TLSRX_HDR_PKT_INT_ERROR_G(x) \ - (((x) >> TLSRX_HDR_PKT_INT_ERROR_S) & TLSRX_HDR_PKT_INT_ERROR_M) -#define TLSRX_HDR_PKT_INT_ERROR_F TLSRX_HDR_PKT_INT_ERROR_V(1U) - -#define TLSRX_HDR_PKT_SPP_ERROR_S 3 -#define TLSRX_HDR_PKT_SPP_ERROR_M 0x1 -#define TLSRX_HDR_PKT_SPP_ERROR_V(x) ((x) << TLSRX_HDR_PKT_SPP_ERROR) -#define TLSRX_HDR_PKT_SPP_ERROR_G(x) \ - (((x) >> TLSRX_HDR_PKT_SPP_ERROR_S) & TLSRX_HDR_PKT_SPP_ERROR_M) -#define TLSRX_HDR_PKT_SPP_ERROR_F TLSRX_HDR_PKT_SPP_ERROR_V(1U) - -#define TLSRX_HDR_PKT_CCDX_ERROR_S 2 -#define TLSRX_HDR_PKT_CCDX_ERROR_M 0x1 -#define TLSRX_HDR_PKT_CCDX_ERROR_V(x) ((x) << TLSRX_HDR_PKT_CCDX_ERROR_S) -#define TLSRX_HDR_PKT_CCDX_ERROR_G(x) \ - (((x) >> TLSRX_HDR_PKT_CCDX_ERROR_S) & TLSRX_HDR_PKT_CCDX_ERROR_M) -#define TLSRX_HDR_PKT_CCDX_ERROR_F TLSRX_HDR_PKT_CCDX_ERROR_V(1U) - -#define TLSRX_HDR_PKT_PAD_ERROR_S 1 -#define TLSRX_HDR_PKT_PAD_ERROR_M 0x1 -#define TLSRX_HDR_PKT_PAD_ERROR_V(x) ((x) << TLSRX_HDR_PKT_PAD_ERROR_S) -#define TLSRX_HDR_PKT_PAD_ERROR_G(x) \ - (((x) >> TLSRX_HDR_PKT_PAD_ERROR_S) & TLSRX_HDR_PKT_PAD_ERROR_M) -#define TLSRX_HDR_PKT_PAD_ERROR_F TLSRX_HDR_PKT_PAD_ERROR_V(1U) - -#define TLSRX_HDR_PKT_MAC_ERROR_S 0 -#define TLSRX_HDR_PKT_MAC_ERROR_M 0x1 -#define TLSRX_HDR_PKT_MAC_ERROR_V(x) ((x) << TLSRX_HDR_PKT_MAC_ERROR) -#define TLSRX_HDR_PKT_MAC_ERROR_G(x) \ - (((x) >> S_TLSRX_HDR_PKT_MAC_ERROR_S) & TLSRX_HDR_PKT_MAC_ERROR_M) -#define TLSRX_HDR_PKT_MAC_ERROR_F TLSRX_HDR_PKT_MAC_ERROR_V(1U) - -#define TLSRX_HDR_PKT_ERROR_M 0x1F -#define CONTENT_TYPE_ERROR 0x7F - -struct ulp_mem_rw { - __be32 cmd; - __be32 len16; /* command length */ - __be32 dlen; /* data length in 32-byte units */ - __be32 lock_addr; -}; - -struct tls_key_wr { - __be32 op_to_compl; - __be32 flowid_len16; - __be32 ftid; - u8 reneg_to_write_rx; - u8 protocol; - __be16 mfs; -}; - -struct tls_key_req { - struct tls_key_wr wr; - struct ulp_mem_rw req; - struct ulptx_idata sc_imm; -}; - -/* - * This lives in skb->cb and is used to chain WRs in a linked list. - */ -struct wr_skb_cb { - struct l2t_skb_cb l2t; /* reserve space for l2t CB */ - struct sk_buff *next_wr; /* next write request */ -}; - -/* Per-skb backlog handler. Run when a socket's backlog is processed. */ -struct blog_skb_cb { - void (*backlog_rcv)(struct sock *sk, struct sk_buff *skb); - struct chtls_dev *cdev; -}; - -/* - * Similar to tcp_skb_cb but with ULP elements added to support TLS, - * etc. - */ -struct ulp_skb_cb { - struct wr_skb_cb wr; /* reserve space for write request */ - u16 flags; /* TCP-like flags */ - u8 psh; - u8 ulp_mode; /* ULP mode/submode of sk_buff */ - u32 seq; /* TCP sequence number */ - union { /* ULP-specific fields */ - struct { - u8 type; - u8 ofld; - u8 iv; - } tls; - } ulp; -}; - -#define ULP_SKB_CB(skb) ((struct ulp_skb_cb *)&((skb)->cb[0])) -#define BLOG_SKB_CB(skb) ((struct blog_skb_cb *)(skb)->cb) - -/* - * Flags for ulp_skb_cb.flags. - */ -enum { - ULPCB_FLAG_NEED_HDR = 1 << 0, /* packet needs a TX_DATA_WR header */ - ULPCB_FLAG_NO_APPEND = 1 << 1, /* don't grow this skb */ - ULPCB_FLAG_BARRIER = 1 << 2, /* set TX_WAIT_IDLE after sending */ - ULPCB_FLAG_HOLD = 1 << 3, /* skb not ready for Tx yet */ - ULPCB_FLAG_COMPL = 1 << 4, /* request WR completion */ - ULPCB_FLAG_URG = 1 << 5, /* urgent data */ - ULPCB_FLAG_TLS_HDR = 1 << 6, /* payload with tls hdr */ - ULPCB_FLAG_NO_HDR = 1 << 7, /* not a ofld wr */ -}; - -/* The ULP mode/submode of an skbuff */ -#define skb_ulp_mode(skb) (ULP_SKB_CB(skb)->ulp_mode) -#define TCP_PAGE(sk) (sk->sk_frag.page) -#define TCP_OFF(sk) (sk->sk_frag.offset) - -static inline struct chtls_dev *to_chtls_dev(struct tls_toe_device *tlsdev) -{ - return container_of(tlsdev, struct chtls_dev, tlsdev); -} - -static inline void csk_set_flag(struct chtls_sock *csk, - enum csk_flags flag) -{ - __set_bit(flag, &csk->flags); -} - -static inline void csk_reset_flag(struct chtls_sock *csk, - enum csk_flags flag) -{ - __clear_bit(flag, &csk->flags); -} - -static inline bool csk_conn_inline(const struct chtls_sock *csk) -{ - return test_bit(CSK_CONN_INLINE, &csk->flags); -} - -static inline int csk_flag(const struct sock *sk, enum csk_flags flag) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - - if (!csk_conn_inline(csk)) - return 0; - return test_bit(flag, &csk->flags); -} - -static inline int csk_flag_nochk(const struct chtls_sock *csk, - enum csk_flags flag) -{ - return test_bit(flag, &csk->flags); -} - -static inline void *cplhdr(struct sk_buff *skb) -{ - return skb->data; -} - -static inline int is_neg_adv(unsigned int status) -{ - return status == CPL_ERR_RTX_NEG_ADVICE || - status == CPL_ERR_KEEPALV_NEG_ADVICE || - status == CPL_ERR_PERSIST_NEG_ADVICE; -} - -static inline void process_cpl_msg(void (*fn)(struct sock *, struct sk_buff *), - struct sock *sk, - struct sk_buff *skb) -{ - skb_reset_mac_header(skb); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - - bh_lock_sock(sk); - if (unlikely(sock_owned_by_user(sk))) { - BLOG_SKB_CB(skb)->backlog_rcv = fn; - __sk_add_backlog(sk, skb); - } else { - fn(sk, skb); - } - bh_unlock_sock(sk); -} - -static inline void chtls_sock_free(struct kref *ref) -{ - struct chtls_sock *csk = container_of(ref, struct chtls_sock, - kref); - kfree(csk); -} - -static inline void __chtls_sock_put(const char *fn, struct chtls_sock *csk) -{ - kref_put(&csk->kref, chtls_sock_free); -} - -static inline void __chtls_sock_get(const char *fn, - struct chtls_sock *csk) -{ - kref_get(&csk->kref); -} - -static inline void send_or_defer(struct sock *sk, struct tcp_sock *tp, - struct sk_buff *skb, int through_l2t) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - - if (through_l2t) { - /* send through L2T */ - cxgb4_l2t_send(csk->egress_dev, skb, csk->l2t_entry); - } else { - /* send directly */ - cxgb4_ofld_send(csk->egress_dev, skb); - } -} - -typedef int (*chtls_handler_func)(struct chtls_dev *, struct sk_buff *); -extern chtls_handler_func chtls_handlers[NUM_CPL_CMDS]; -void chtls_install_cpl_ops(struct sock *sk); -int chtls_init_kmap(struct chtls_dev *cdev, struct cxgb4_lld_info *lldi); -void chtls_listen_stop(struct chtls_dev *cdev, struct sock *sk); -int chtls_listen_start(struct chtls_dev *cdev, struct sock *sk); -void chtls_close(struct sock *sk, long timeout); -int chtls_disconnect(struct sock *sk, int flags); -void chtls_shutdown(struct sock *sk, int how); -void chtls_destroy_sock(struct sock *sk); -int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -int chtls_recvmsg(struct sock *sk, struct msghdr *msg, - size_t len, int flags); -void chtls_splice_eof(struct socket *sock); -int send_tx_flowc_wr(struct sock *sk, int compl, - u32 snd_nxt, u32 rcv_nxt); -void chtls_tcp_push(struct sock *sk, int flags); -int chtls_push_frames(struct chtls_sock *csk, int comp); -void chtls_set_tcb_field_rpl_skb(struct sock *sk, u16 word, - u64 mask, u64 val, u8 cookie, - int through_l2t); -int chtls_setkey(struct chtls_sock *csk, u32 keylen, u32 mode, int cipher_type); -void chtls_set_quiesce_ctrl(struct sock *sk, int val); -void skb_entail(struct sock *sk, struct sk_buff *skb, int flags); -unsigned int keyid_to_addr(int start_addr, int keyid); -void free_tls_keyid(struct sock *sk); -#endif diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c deleted file mode 100644 index 0e3e5cf52c2c..000000000000 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ /dev/null @@ -1,2336 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2018 Chelsio Communications, Inc. - * - * Written by: Atul Gupta (atul.gupta@chelsio.com) - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "chtls.h" -#include "chtls_cm.h" -#include "clip_tbl.h" -#include "t4_tcb.h" - -/* - * State transitions and actions for close. Note that if we are in SYN_SENT - * we remain in that state as we cannot control a connection while it's in - * SYN_SENT; such connections are allowed to establish and are then aborted. - */ -static unsigned char new_state[16] = { - /* current state: new state: action: */ - /* (Invalid) */ TCP_CLOSE, - /* TCP_ESTABLISHED */ TCP_FIN_WAIT1 | TCP_ACTION_FIN, - /* TCP_SYN_SENT */ TCP_SYN_SENT, - /* TCP_SYN_RECV */ TCP_FIN_WAIT1 | TCP_ACTION_FIN, - /* TCP_FIN_WAIT1 */ TCP_FIN_WAIT1, - /* TCP_FIN_WAIT2 */ TCP_FIN_WAIT2, - /* TCP_TIME_WAIT */ TCP_CLOSE, - /* TCP_CLOSE */ TCP_CLOSE, - /* TCP_CLOSE_WAIT */ TCP_LAST_ACK | TCP_ACTION_FIN, - /* TCP_LAST_ACK */ TCP_LAST_ACK, - /* TCP_LISTEN */ TCP_CLOSE, - /* TCP_CLOSING */ TCP_CLOSING, -}; - -static struct chtls_sock *chtls_sock_create(struct chtls_dev *cdev) -{ - struct chtls_sock *csk = kzalloc_obj(*csk, GFP_ATOMIC); - - if (!csk) - return NULL; - - csk->txdata_skb_cache = alloc_skb(TXDATA_SKB_LEN, GFP_ATOMIC); - if (!csk->txdata_skb_cache) { - kfree(csk); - return NULL; - } - - kref_init(&csk->kref); - csk->cdev = cdev; - skb_queue_head_init(&csk->txq); - csk->wr_skb_head = NULL; - csk->wr_skb_tail = NULL; - csk->mss = MAX_MSS; - csk->tlshws.ofld = 1; - csk->tlshws.txkey = -1; - csk->tlshws.rxkey = -1; - csk->tlshws.mfs = TLS_MFS; - skb_queue_head_init(&csk->tlshws.sk_recv_queue); - return csk; -} - -static void chtls_sock_release(struct kref *ref) -{ - struct chtls_sock *csk = - container_of(ref, struct chtls_sock, kref); - - kfree(csk); -} - -static struct net_device *chtls_find_netdev(struct chtls_dev *cdev, - struct sock *sk) -{ - struct adapter *adap = pci_get_drvdata(cdev->pdev); - struct net_device *ndev = cdev->ports[0]; -#if IS_ENABLED(CONFIG_IPV6) - struct net_device *temp; - int addr_type; -#endif - int i; - - switch (sk->sk_family) { - case PF_INET: - if (likely(!inet_sk(sk)->inet_rcv_saddr)) - return ndev; - ndev = __ip_dev_find(&init_net, inet_sk(sk)->inet_rcv_saddr, false); - break; -#if IS_ENABLED(CONFIG_IPV6) - case PF_INET6: - addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); - if (likely(addr_type == IPV6_ADDR_ANY)) - return ndev; - - for_each_netdev_rcu(&init_net, temp) { - if (ipv6_chk_addr(&init_net, (struct in6_addr *) - &sk->sk_v6_rcv_saddr, temp, 1)) { - ndev = temp; - break; - } - } - break; -#endif - default: - return NULL; - } - - if (!ndev) - return NULL; - - if (is_vlan_dev(ndev)) - ndev = vlan_dev_real_dev(ndev); - - for_each_port(adap, i) - if (cdev->ports[i] == ndev) - return ndev; - return NULL; -} - -static void assign_rxopt(struct sock *sk, unsigned int opt) -{ - const struct chtls_dev *cdev; - struct chtls_sock *csk; - struct tcp_sock *tp; - - csk = rcu_dereference_sk_user_data(sk); - tp = tcp_sk(sk); - - cdev = csk->cdev; - tp->tcp_header_len = sizeof(struct tcphdr); - tp->rx_opt.mss_clamp = cdev->mtus[TCPOPT_MSS_G(opt)] - 40; - tp->mss_cache = tp->rx_opt.mss_clamp; - tp->rx_opt.tstamp_ok = TCPOPT_TSTAMP_G(opt); - tp->rx_opt.snd_wscale = TCPOPT_SACK_G(opt); - tp->rx_opt.wscale_ok = TCPOPT_WSCALE_OK_G(opt); - SND_WSCALE(tp) = TCPOPT_SND_WSCALE_G(opt); - if (!tp->rx_opt.wscale_ok) - tp->rx_opt.rcv_wscale = 0; - if (tp->rx_opt.tstamp_ok) { - tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; - tp->rx_opt.mss_clamp -= TCPOLEN_TSTAMP_ALIGNED; - } else if (csk->opt2 & TSTAMPS_EN_F) { - csk->opt2 &= ~TSTAMPS_EN_F; - csk->mtu_idx = TCPOPT_MSS_G(opt); - } -} - -static void chtls_purge_receive_queue(struct sock *sk) -{ - struct sk_buff *skb; - - while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { - skb_dstref_steal(skb); - kfree_skb(skb); - } -} - -static void chtls_purge_write_queue(struct sock *sk) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct sk_buff *skb; - - while ((skb = __skb_dequeue(&csk->txq))) { - sk->sk_wmem_queued -= skb->truesize; - __kfree_skb(skb); - } -} - -static void chtls_purge_recv_queue(struct sock *sk) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct chtls_hws *tlsk = &csk->tlshws; - struct sk_buff *skb; - - while ((skb = __skb_dequeue(&tlsk->sk_recv_queue)) != NULL) { - skb_dstref_steal(skb); - kfree_skb(skb); - } -} - -static void abort_arp_failure(void *handle, struct sk_buff *skb) -{ - struct cpl_abort_req *req = cplhdr(skb); - struct chtls_dev *cdev; - - cdev = (struct chtls_dev *)handle; - req->cmd = CPL_ABORT_NO_RST; - cxgb4_ofld_send(cdev->lldi->ports[0], skb); -} - -static struct sk_buff *alloc_ctrl_skb(struct sk_buff *skb, int len) -{ - if (likely(skb && !skb_shared(skb) && !skb_cloned(skb))) { - __skb_trim(skb, 0); - refcount_inc(&skb->users); - } else { - skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL); - } - return skb; -} - -static void chtls_send_abort(struct sock *sk, int mode, struct sk_buff *skb) -{ - struct cpl_abort_req *req; - struct chtls_sock *csk; - struct tcp_sock *tp; - - csk = rcu_dereference_sk_user_data(sk); - tp = tcp_sk(sk); - - if (!skb) - skb = alloc_ctrl_skb(csk->txdata_skb_cache, sizeof(*req)); - - req = (struct cpl_abort_req *)skb_put(skb, sizeof(*req)); - INIT_TP_WR_CPL(req, CPL_ABORT_REQ, csk->tid); - skb_set_queue_mapping(skb, (csk->txq_idx << 1) | CPL_PRIORITY_DATA); - req->rsvd0 = htonl(tp->snd_nxt); - req->rsvd1 = !csk_flag_nochk(csk, CSK_TX_DATA_SENT); - req->cmd = mode; - t4_set_arp_err_handler(skb, csk->cdev, abort_arp_failure); - send_or_defer(sk, tp, skb, mode == CPL_ABORT_SEND_RST); -} - -static void chtls_send_reset(struct sock *sk, int mode, struct sk_buff *skb) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - - if (unlikely(csk_flag_nochk(csk, CSK_ABORT_SHUTDOWN) || - !csk->cdev)) { - if (sk->sk_state == TCP_SYN_RECV) - csk_set_flag(csk, CSK_RST_ABORTED); - goto out; - } - - if (!csk_flag_nochk(csk, CSK_TX_DATA_SENT)) { - struct tcp_sock *tp = tcp_sk(sk); - - if (send_tx_flowc_wr(sk, 0, tp->snd_nxt, tp->rcv_nxt) < 0) - WARN_ONCE(1, "send tx flowc error"); - csk_set_flag(csk, CSK_TX_DATA_SENT); - } - - csk_set_flag(csk, CSK_ABORT_RPL_PENDING); - chtls_purge_write_queue(sk); - - csk_set_flag(csk, CSK_ABORT_SHUTDOWN); - if (sk->sk_state != TCP_SYN_RECV) - chtls_send_abort(sk, mode, skb); - else - chtls_set_tcb_field_rpl_skb(sk, TCB_T_FLAGS_W, - TCB_T_FLAGS_V(TCB_T_FLAGS_M), 0, - TCB_FIELD_COOKIE_TFLAG, 1); - - return; -out: - kfree_skb(skb); -} - -static void release_tcp_port(struct sock *sk) -{ - if (inet_csk(sk)->icsk_bind_hash) - inet_put_port(sk); -} - -static void tcp_uncork(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (tp->nonagle & TCP_NAGLE_CORK) { - tp->nonagle &= ~TCP_NAGLE_CORK; - chtls_tcp_push(sk, 0); - } -} - -static void chtls_close_conn(struct sock *sk) -{ - struct cpl_close_con_req *req; - struct chtls_sock *csk; - struct sk_buff *skb; - unsigned int tid; - unsigned int len; - - len = roundup(sizeof(struct cpl_close_con_req), 16); - csk = rcu_dereference_sk_user_data(sk); - tid = csk->tid; - - skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL); - req = (struct cpl_close_con_req *)__skb_put(skb, len); - memset(req, 0, len); - req->wr.wr_hi = htonl(FW_WR_OP_V(FW_TP_WR) | - FW_WR_IMMDLEN_V(sizeof(*req) - - sizeof(req->wr))); - req->wr.wr_mid = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*req), 16)) | - FW_WR_FLOWID_V(tid)); - - OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid)); - - tcp_uncork(sk); - skb_entail(sk, skb, ULPCB_FLAG_NO_HDR | ULPCB_FLAG_NO_APPEND); - if (sk->sk_state != TCP_SYN_SENT) - chtls_push_frames(csk, 1); -} - -/* - * Perform a state transition during close and return the actions indicated - * for the transition. Do not make this function inline, the main reason - * it exists at all is to avoid multiple inlining of tcp_set_state. - */ -static int make_close_transition(struct sock *sk) -{ - int next = (int)new_state[sk->sk_state]; - - tcp_set_state(sk, next & TCP_STATE_MASK); - return next & TCP_ACTION_FIN; -} - -void chtls_close(struct sock *sk, long timeout) -{ - int data_lost, prev_state; - struct chtls_sock *csk; - - csk = rcu_dereference_sk_user_data(sk); - - lock_sock(sk); - sk->sk_shutdown |= SHUTDOWN_MASK; - - data_lost = skb_queue_len(&sk->sk_receive_queue); - data_lost |= skb_queue_len(&csk->tlshws.sk_recv_queue); - chtls_purge_recv_queue(sk); - chtls_purge_receive_queue(sk); - - if (sk->sk_state == TCP_CLOSE) { - goto wait; - } else if (data_lost || sk->sk_state == TCP_SYN_SENT) { - chtls_send_reset(sk, CPL_ABORT_SEND_RST, NULL); - release_tcp_port(sk); - goto unlock; - } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { - sk->sk_prot->disconnect(sk, 0); - } else if (make_close_transition(sk)) { - chtls_close_conn(sk); - } -wait: - if (timeout) - sk_stream_wait_close(sk, timeout); - -unlock: - prev_state = sk->sk_state; - sock_hold(sk); - sock_orphan(sk); - - release_sock(sk); - - local_bh_disable(); - bh_lock_sock(sk); - - if (prev_state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) - goto out; - - if (sk->sk_state == TCP_FIN_WAIT2 && tcp_sk(sk)->linger2 < 0 && - !csk_flag(sk, CSK_ABORT_SHUTDOWN)) { - struct sk_buff *skb; - - skb = alloc_skb(sizeof(struct cpl_abort_req), GFP_ATOMIC); - if (skb) - chtls_send_reset(sk, CPL_ABORT_SEND_RST, skb); - } - - if (sk->sk_state == TCP_CLOSE) - inet_csk_destroy_sock(sk); - -out: - bh_unlock_sock(sk); - local_bh_enable(); - sock_put(sk); -} - -/* - * Wait until a socket enters on of the given states. - */ -static int wait_for_states(struct sock *sk, unsigned int states) -{ - DECLARE_WAITQUEUE(wait, current); - struct socket_wq _sk_wq; - long current_timeo; - int err = 0; - - current_timeo = 200; - - /* - * We want this to work even when there's no associated struct socket. - * In that case we provide a temporary wait_queue_head_t. - */ - if (!sk->sk_wq) { - init_waitqueue_head(&_sk_wq.wait); - _sk_wq.fasync_list = NULL; - init_rcu_head_on_stack(&_sk_wq.rcu); - RCU_INIT_POINTER(sk->sk_wq, &_sk_wq); - } - - add_wait_queue(sk_sleep(sk), &wait); - while (!sk_in_state(sk, states)) { - if (!current_timeo) { - err = -EBUSY; - break; - } - if (signal_pending(current)) { - err = sock_intr_errno(current_timeo); - break; - } - set_current_state(TASK_UNINTERRUPTIBLE); - release_sock(sk); - if (!sk_in_state(sk, states)) - current_timeo = schedule_timeout(current_timeo); - __set_current_state(TASK_RUNNING); - lock_sock(sk); - } - remove_wait_queue(sk_sleep(sk), &wait); - - if (rcu_dereference(sk->sk_wq) == &_sk_wq) - sk->sk_wq = NULL; - return err; -} - -int chtls_disconnect(struct sock *sk, int flags) -{ - struct tcp_sock *tp; - int err; - - tp = tcp_sk(sk); - chtls_purge_recv_queue(sk); - chtls_purge_receive_queue(sk); - chtls_purge_write_queue(sk); - - if (sk->sk_state != TCP_CLOSE) { - sk->sk_err = ECONNRESET; - chtls_send_reset(sk, CPL_ABORT_SEND_RST, NULL); - err = wait_for_states(sk, TCPF_CLOSE); - if (err) - return err; - } - chtls_purge_recv_queue(sk); - chtls_purge_receive_queue(sk); - tp->max_window = 0xFFFF << (tp->rx_opt.snd_wscale); - return tcp_disconnect(sk, flags); -} - -#define SHUTDOWN_ELIGIBLE_STATE (TCPF_ESTABLISHED | \ - TCPF_SYN_RECV | TCPF_CLOSE_WAIT) -void chtls_shutdown(struct sock *sk, int how) -{ - if ((how & SEND_SHUTDOWN) && - sk_in_state(sk, SHUTDOWN_ELIGIBLE_STATE) && - make_close_transition(sk)) - chtls_close_conn(sk); -} - -void chtls_destroy_sock(struct sock *sk) -{ - struct chtls_sock *csk; - - csk = rcu_dereference_sk_user_data(sk); - chtls_purge_recv_queue(sk); - csk->ulp_mode = ULP_MODE_NONE; - chtls_purge_write_queue(sk); - free_tls_keyid(sk); - kref_put(&csk->kref, chtls_sock_release); - if (sk->sk_family == AF_INET) - sk->sk_prot = &tcp_prot; -#if IS_ENABLED(CONFIG_IPV6) - else - sk->sk_prot = &tcpv6_prot; -#endif - sk->sk_prot->destroy(sk); -} - -static void reset_listen_child(struct sock *child) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(child); - struct sk_buff *skb; - - skb = alloc_ctrl_skb(csk->txdata_skb_cache, - sizeof(struct cpl_abort_req)); - - chtls_send_reset(child, CPL_ABORT_SEND_RST, skb); - sock_orphan(child); - tcp_orphan_count_inc(); - if (child->sk_state == TCP_CLOSE) - inet_csk_destroy_sock(child); -} - -static void chtls_disconnect_acceptq(struct sock *listen_sk) -{ - struct request_sock **pprev; - - pprev = ACCEPT_QUEUE(listen_sk); - while (*pprev) { - struct request_sock *req = *pprev; - - if (req->rsk_ops == &chtls_rsk_ops || - req->rsk_ops == &chtls_rsk_opsv6) { - struct sock *child = req->sk; - - *pprev = req->dl_next; - sk_acceptq_removed(listen_sk); - reqsk_put(req); - sock_hold(child); - local_bh_disable(); - bh_lock_sock(child); - release_tcp_port(child); - reset_listen_child(child); - bh_unlock_sock(child); - local_bh_enable(); - sock_put(child); - } else { - pprev = &req->dl_next; - } - } -} - -static int listen_hashfn(const struct sock *sk) -{ - return ((unsigned long)sk >> 10) & (LISTEN_INFO_HASH_SIZE - 1); -} - -static struct listen_info *listen_hash_add(struct chtls_dev *cdev, - struct sock *sk, - unsigned int stid) -{ - struct listen_info *p = kmalloc_obj(*p); - - if (p) { - int key = listen_hashfn(sk); - - p->sk = sk; - p->stid = stid; - spin_lock(&cdev->listen_lock); - p->next = cdev->listen_hash_tab[key]; - cdev->listen_hash_tab[key] = p; - spin_unlock(&cdev->listen_lock); - } - return p; -} - -static int listen_hash_find(struct chtls_dev *cdev, - struct sock *sk) -{ - struct listen_info *p; - int stid = -1; - int key; - - key = listen_hashfn(sk); - - spin_lock(&cdev->listen_lock); - for (p = cdev->listen_hash_tab[key]; p; p = p->next) - if (p->sk == sk) { - stid = p->stid; - break; - } - spin_unlock(&cdev->listen_lock); - return stid; -} - -static int listen_hash_del(struct chtls_dev *cdev, - struct sock *sk) -{ - struct listen_info *p, **prev; - int stid = -1; - int key; - - key = listen_hashfn(sk); - prev = &cdev->listen_hash_tab[key]; - - spin_lock(&cdev->listen_lock); - for (p = *prev; p; prev = &p->next, p = p->next) - if (p->sk == sk) { - stid = p->stid; - *prev = p->next; - kfree(p); - break; - } - spin_unlock(&cdev->listen_lock); - return stid; -} - -static void cleanup_syn_rcv_conn(struct sock *child, struct sock *parent) -{ - struct request_sock *req; - struct chtls_sock *csk; - - csk = rcu_dereference_sk_user_data(child); - req = csk->passive_reap_next; - - reqsk_queue_removed(&inet_csk(parent)->icsk_accept_queue, req); - __skb_unlink((struct sk_buff *)&csk->synq, &csk->listen_ctx->synq); - chtls_reqsk_free(req); - csk->passive_reap_next = NULL; -} - -static void chtls_reset_synq(struct listen_ctx *listen_ctx) -{ - struct sock *listen_sk = listen_ctx->lsk; - - while (!skb_queue_empty(&listen_ctx->synq)) { - struct chtls_sock *csk = - container_of((struct synq *)skb_peek - (&listen_ctx->synq), struct chtls_sock, synq); - struct sock *child = csk->sk; - - cleanup_syn_rcv_conn(child, listen_sk); - sock_hold(child); - local_bh_disable(); - bh_lock_sock(child); - release_tcp_port(child); - reset_listen_child(child); - bh_unlock_sock(child); - local_bh_enable(); - sock_put(child); - } -} - -int chtls_listen_start(struct chtls_dev *cdev, struct sock *sk) -{ - struct net_device *ndev; -#if IS_ENABLED(CONFIG_IPV6) - bool clip_valid = false; -#endif - struct listen_ctx *ctx; - struct adapter *adap; - struct port_info *pi; - int ret = 0; - int stid; - - rcu_read_lock(); - ndev = chtls_find_netdev(cdev, sk); - rcu_read_unlock(); - if (!ndev) - return -EBADF; - - pi = netdev_priv(ndev); - adap = pi->adapter; - if (!(adap->flags & CXGB4_FULL_INIT_DONE)) - return -EBADF; - - if (listen_hash_find(cdev, sk) >= 0) /* already have it */ - return -EADDRINUSE; - - ctx = kmalloc_obj(*ctx); - if (!ctx) - return -ENOMEM; - - __module_get(THIS_MODULE); - ctx->lsk = sk; - ctx->cdev = cdev; - ctx->state = T4_LISTEN_START_PENDING; - skb_queue_head_init(&ctx->synq); - - stid = cxgb4_alloc_stid(cdev->tids, sk->sk_family, ctx); - if (stid < 0) - goto free_ctx; - - sock_hold(sk); - if (!listen_hash_add(cdev, sk, stid)) - goto free_stid; - - if (sk->sk_family == PF_INET) { - ret = cxgb4_create_server(ndev, stid, - inet_sk(sk)->inet_rcv_saddr, - inet_sk(sk)->inet_sport, 0, - cdev->lldi->rxq_ids[0]); -#if IS_ENABLED(CONFIG_IPV6) - } else { - int addr_type; - - addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); - if (addr_type != IPV6_ADDR_ANY) { - ret = cxgb4_clip_get(ndev, (const u32 *) - &sk->sk_v6_rcv_saddr, 1); - if (ret) - goto del_hash; - clip_valid = true; - } - ret = cxgb4_create_server6(ndev, stid, - &sk->sk_v6_rcv_saddr, - inet_sk(sk)->inet_sport, - cdev->lldi->rxq_ids[0]); -#endif - } - if (ret > 0) - ret = net_xmit_errno(ret); - if (ret) - goto del_hash; - return 0; -del_hash: -#if IS_ENABLED(CONFIG_IPV6) - if (clip_valid) - cxgb4_clip_release(ndev, (const u32 *)&sk->sk_v6_rcv_saddr, 1); -#endif - listen_hash_del(cdev, sk); -free_stid: - cxgb4_free_stid(cdev->tids, stid, sk->sk_family); - sock_put(sk); -free_ctx: - kfree(ctx); - module_put(THIS_MODULE); - return -EBADF; -} - -void chtls_listen_stop(struct chtls_dev *cdev, struct sock *sk) -{ - struct listen_ctx *listen_ctx; - int stid; - - stid = listen_hash_del(cdev, sk); - if (stid < 0) - return; - - listen_ctx = (struct listen_ctx *)lookup_stid(cdev->tids, stid); - chtls_reset_synq(listen_ctx); - - cxgb4_remove_server(cdev->lldi->ports[0], stid, - cdev->lldi->rxq_ids[0], sk->sk_family == PF_INET6); - -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { - struct net_device *ndev = chtls_find_netdev(cdev, sk); - int addr_type = 0; - - addr_type = ipv6_addr_type((const struct in6_addr *) - &sk->sk_v6_rcv_saddr); - if (addr_type != IPV6_ADDR_ANY) - cxgb4_clip_release(ndev, (const u32 *) - &sk->sk_v6_rcv_saddr, 1); - } -#endif - chtls_disconnect_acceptq(sk); -} - -static int chtls_pass_open_rpl(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_pass_open_rpl *rpl = cplhdr(skb) + RSS_HDR; - unsigned int stid = GET_TID(rpl); - struct listen_ctx *listen_ctx; - - listen_ctx = (struct listen_ctx *)lookup_stid(cdev->tids, stid); - if (!listen_ctx) - return CPL_RET_BUF_DONE; - - if (listen_ctx->state == T4_LISTEN_START_PENDING) { - listen_ctx->state = T4_LISTEN_STARTED; - return CPL_RET_BUF_DONE; - } - - if (rpl->status != CPL_ERR_NONE) { - pr_info("Unexpected PASS_OPEN_RPL status %u for STID %u\n", - rpl->status, stid); - } else { - cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family); - sock_put(listen_ctx->lsk); - kfree(listen_ctx); - module_put(THIS_MODULE); - } - return CPL_RET_BUF_DONE; -} - -static int chtls_close_listsrv_rpl(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_close_listsvr_rpl *rpl = cplhdr(skb) + RSS_HDR; - struct listen_ctx *listen_ctx; - unsigned int stid; - void *data; - - stid = GET_TID(rpl); - data = lookup_stid(cdev->tids, stid); - listen_ctx = (struct listen_ctx *)data; - - if (rpl->status != CPL_ERR_NONE) { - pr_info("Unexpected CLOSE_LISTSRV_RPL status %u for STID %u\n", - rpl->status, stid); - } else { - cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family); - sock_put(listen_ctx->lsk); - kfree(listen_ctx); - module_put(THIS_MODULE); - } - return CPL_RET_BUF_DONE; -} - -static void chtls_purge_wr_queue(struct sock *sk) -{ - struct sk_buff *skb; - - while ((skb = dequeue_wr(sk)) != NULL) - kfree_skb(skb); -} - -static void chtls_release_resources(struct sock *sk) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct chtls_dev *cdev = csk->cdev; - unsigned int tid = csk->tid; - struct tid_info *tids; - - if (!cdev) - return; - - tids = cdev->tids; - kfree_skb(csk->txdata_skb_cache); - csk->txdata_skb_cache = NULL; - - if (csk->wr_credits != csk->wr_max_credits) { - chtls_purge_wr_queue(sk); - chtls_reset_wr_list(csk); - } - - if (csk->l2t_entry) { - cxgb4_l2t_release(csk->l2t_entry); - csk->l2t_entry = NULL; - } - - if (sk->sk_state != TCP_SYN_SENT) { - cxgb4_remove_tid(tids, csk->port_id, tid, sk->sk_family); - sock_put(sk); - } -} - -static void chtls_conn_done(struct sock *sk) -{ - if (sock_flag(sk, SOCK_DEAD)) - chtls_purge_receive_queue(sk); - sk_wakeup_sleepers(sk, 0); - tcp_done(sk); -} - -static void do_abort_syn_rcv(struct sock *child, struct sock *parent) -{ - /* - * If the server is still open we clean up the child connection, - * otherwise the server already did the clean up as it was purging - * its SYN queue and the skb was just sitting in its backlog. - */ - if (likely(parent->sk_state == TCP_LISTEN)) { - cleanup_syn_rcv_conn(child, parent); - /* Without the below call to sock_orphan, - * we leak the socket resource with syn_flood test - * as inet_csk_destroy_sock will not be called - * in tcp_done since SOCK_DEAD flag is not set. - * Kernel handles this differently where new socket is - * created only after 3 way handshake is done. - */ - sock_orphan(child); - tcp_orphan_count_inc(); - chtls_release_resources(child); - chtls_conn_done(child); - } else { - if (csk_flag(child, CSK_RST_ABORTED)) { - chtls_release_resources(child); - chtls_conn_done(child); - } - } -} - -static void pass_open_abort(struct sock *child, struct sock *parent, - struct sk_buff *skb) -{ - do_abort_syn_rcv(child, parent); - kfree_skb(skb); -} - -static void bl_pass_open_abort(struct sock *lsk, struct sk_buff *skb) -{ - pass_open_abort(skb->sk, lsk, skb); -} - -static void chtls_pass_open_arp_failure(struct sock *sk, - struct sk_buff *skb) -{ - const struct request_sock *oreq; - struct chtls_sock *csk; - struct chtls_dev *cdev; - struct sock *parent; - void *data; - - csk = rcu_dereference_sk_user_data(sk); - cdev = csk->cdev; - - /* - * If the connection is being aborted due to the parent listening - * socket going away there's nothing to do, the ABORT_REQ will close - * the connection. - */ - if (csk_flag(sk, CSK_ABORT_RPL_PENDING)) { - kfree_skb(skb); - return; - } - - oreq = csk->passive_reap_next; - data = lookup_stid(cdev->tids, oreq->ts_recent); - parent = ((struct listen_ctx *)data)->lsk; - - bh_lock_sock(parent); - if (!sock_owned_by_user(parent)) { - pass_open_abort(sk, parent, skb); - } else { - BLOG_SKB_CB(skb)->backlog_rcv = bl_pass_open_abort; - __sk_add_backlog(parent, skb); - } - bh_unlock_sock(parent); -} - -static void chtls_accept_rpl_arp_failure(void *handle, - struct sk_buff *skb) -{ - struct sock *sk = (struct sock *)handle; - - sock_hold(sk); - process_cpl_msg(chtls_pass_open_arp_failure, sk, skb); - sock_put(sk); -} - -static unsigned int chtls_select_mss(const struct chtls_sock *csk, - unsigned int pmtu, - struct cpl_pass_accept_req *req) -{ - struct chtls_dev *cdev; - struct dst_entry *dst; - unsigned int tcpoptsz; - unsigned int iphdrsz; - unsigned int mtu_idx; - struct tcp_sock *tp; - unsigned int mss; - struct sock *sk; - u16 user_mss; - - mss = ntohs(req->tcpopt.mss); - sk = csk->sk; - dst = __sk_dst_get(sk); - cdev = csk->cdev; - tp = tcp_sk(sk); - tcpoptsz = 0; - -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - iphdrsz = sizeof(struct ipv6hdr) + sizeof(struct tcphdr); - else -#endif - iphdrsz = sizeof(struct iphdr) + sizeof(struct tcphdr); - if (req->tcpopt.tstamp) - tcpoptsz += round_up(TCPOLEN_TIMESTAMP, 4); - - tp->advmss = dst_metric_advmss(dst); - user_mss = USER_MSS(tp); - if (user_mss && tp->advmss > user_mss) - tp->advmss = user_mss; - if (tp->advmss > pmtu - iphdrsz) - tp->advmss = pmtu - iphdrsz; - if (mss && tp->advmss > mss) - tp->advmss = mss; - - tp->advmss = cxgb4_best_aligned_mtu(cdev->lldi->mtus, - iphdrsz + tcpoptsz, - tp->advmss - tcpoptsz, - 8, &mtu_idx); - tp->advmss -= iphdrsz; - - inet_csk(sk)->icsk_pmtu_cookie = pmtu; - return mtu_idx; -} - -static unsigned int select_rcv_wscale(int space, int wscale_ok, int win_clamp) -{ - int wscale = 0; - - if (space > MAX_RCV_WND) - space = MAX_RCV_WND; - if (win_clamp && win_clamp < space) - space = win_clamp; - - if (wscale_ok) { - while (wscale < 14 && (65535 << wscale) < space) - wscale++; - } - return wscale; -} - -static void chtls_pass_accept_rpl(struct sk_buff *skb, - struct cpl_pass_accept_req *req, - unsigned int tid) - -{ - struct cpl_t5_pass_accept_rpl *rpl5; - struct cxgb4_lld_info *lldi; - const struct tcphdr *tcph; - const struct tcp_sock *tp; - struct chtls_sock *csk; - unsigned int len; - struct sock *sk; - u32 opt2, hlen; - u64 opt0; - - sk = skb->sk; - tp = tcp_sk(sk); - csk = sk->sk_user_data; - csk->tid = tid; - lldi = csk->cdev->lldi; - len = roundup(sizeof(*rpl5), 16); - - rpl5 = __skb_put_zero(skb, len); - INIT_TP_WR(rpl5, tid); - - OPCODE_TID(rpl5) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL, - csk->tid)); - csk->mtu_idx = chtls_select_mss(csk, dst_mtu(__sk_dst_get(sk)), - req); - opt0 = TCAM_BYPASS_F | - WND_SCALE_V(RCV_WSCALE(tp)) | - MSS_IDX_V(csk->mtu_idx) | - L2T_IDX_V(csk->l2t_entry->idx) | - NAGLE_V(!(tp->nonagle & TCP_NAGLE_OFF)) | - TX_CHAN_V(csk->tx_chan) | - SMAC_SEL_V(csk->smac_idx) | - DSCP_V(csk->tos >> 2) | - ULP_MODE_V(ULP_MODE_TLS) | - RCV_BUFSIZ_V(min(tp->rcv_wnd >> 10, RCV_BUFSIZ_M)); - - opt2 = RX_CHANNEL_V(0) | - RSS_QUEUE_VALID_F | RSS_QUEUE_V(csk->rss_qid); - - if (!is_t5(lldi->adapter_type)) - opt2 |= RX_FC_DISABLE_F; - if (req->tcpopt.tstamp) - opt2 |= TSTAMPS_EN_F; - if (req->tcpopt.sack) - opt2 |= SACK_EN_F; - hlen = ntohl(req->hdr_len); - - tcph = (struct tcphdr *)((u8 *)(req + 1) + - T6_ETH_HDR_LEN_G(hlen) + T6_IP_HDR_LEN_G(hlen)); - if (tcph->ece && tcph->cwr) - opt2 |= CCTRL_ECN_V(1); - opt2 |= CONG_CNTRL_V(CONG_ALG_NEWRENO); - opt2 |= T5_ISS_F; - opt2 |= T5_OPT_2_VALID_F; - opt2 |= WND_SCALE_EN_V(WSCALE_OK(tp)); - rpl5->opt0 = cpu_to_be64(opt0); - rpl5->opt2 = cpu_to_be32(opt2); - rpl5->iss = cpu_to_be32((get_random_u32() & ~7UL) - 1); - set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id); - t4_set_arp_err_handler(skb, sk, chtls_accept_rpl_arp_failure); - cxgb4_l2t_send(csk->egress_dev, skb, csk->l2t_entry); -} - -static void inet_inherit_port(struct sock *lsk, struct sock *newsk) -{ - local_bh_disable(); - __inet_inherit_port(lsk, newsk); - local_bh_enable(); -} - -static int chtls_backlog_rcv(struct sock *sk, struct sk_buff *skb) -{ - if (skb->protocol) { - kfree_skb(skb); - return 0; - } - BLOG_SKB_CB(skb)->backlog_rcv(sk, skb); - return 0; -} - -static void chtls_set_tcp_window(struct chtls_sock *csk) -{ - struct net_device *ndev = csk->egress_dev; - struct port_info *pi = netdev_priv(ndev); - unsigned int linkspeed; - u8 scale; - - linkspeed = pi->link_cfg.speed; - scale = linkspeed / SPEED_10000; -#define CHTLS_10G_RCVWIN (256 * 1024) - csk->rcv_win = CHTLS_10G_RCVWIN; - if (scale) - csk->rcv_win *= scale; -#define CHTLS_10G_SNDWIN (256 * 1024) - csk->snd_win = CHTLS_10G_SNDWIN; - if (scale) - csk->snd_win *= scale; -} - -static struct sock *chtls_recv_sock(struct sock *lsk, - struct request_sock *oreq, - void *network_hdr, - const struct cpl_pass_accept_req *req, - struct chtls_dev *cdev) -{ - struct adapter *adap = pci_get_drvdata(cdev->pdev); - struct neighbour *n = NULL; - struct inet_sock *newinet; - const struct iphdr *iph; - struct tls_context *ctx; - struct net_device *ndev; - struct chtls_sock *csk; - struct dst_entry *dst; - struct tcp_sock *tp; - struct sock *newsk; - bool found = false; - u16 port_id; - int rxq_idx; - int step, i; - - iph = (const struct iphdr *)network_hdr; - newsk = tcp_create_openreq_child(lsk, oreq, cdev->askb); - if (!newsk) - goto free_oreq; - - if (lsk->sk_family == AF_INET) { - dst = inet_csk_route_child_sock(lsk, newsk, oreq); - if (!dst) - goto free_sk; - - n = dst_neigh_lookup(dst, &iph->saddr); -#if IS_ENABLED(CONFIG_IPV6) - } else { - const struct ipv6hdr *ip6h; - struct flowi6 fl6; - - ip6h = (const struct ipv6hdr *)network_hdr; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_TCP; - fl6.saddr = ip6h->daddr; - fl6.daddr = ip6h->saddr; - fl6.fl6_dport = inet_rsk(oreq)->ir_rmt_port; - fl6.fl6_sport = htons(inet_rsk(oreq)->ir_num); - security_req_classify_flow(oreq, flowi6_to_flowi_common(&fl6)); - dst = ip6_dst_lookup_flow(sock_net(lsk), lsk, &fl6, NULL); - if (IS_ERR(dst)) - goto free_sk; - n = dst_neigh_lookup(dst, &ip6h->saddr); -#endif - } - if (!n || !n->dev) - goto free_dst; - - ndev = n->dev; - if (is_vlan_dev(ndev)) - ndev = vlan_dev_real_dev(ndev); - - for_each_port(adap, i) - if (cdev->ports[i] == ndev) - found = true; - - if (!found) - goto free_dst; - - port_id = cxgb4_port_idx(ndev); - - csk = chtls_sock_create(cdev); - if (!csk) - goto free_dst; - - csk->l2t_entry = cxgb4_l2t_get(cdev->lldi->l2t, n, ndev, 0); - if (!csk->l2t_entry) - goto free_csk; - - newsk->sk_user_data = csk; - newsk->sk_backlog_rcv = chtls_backlog_rcv; - - tp = tcp_sk(newsk); - newinet = inet_sk(newsk); - - if (iph->version == 0x4) { - newinet->inet_daddr = iph->saddr; - newinet->inet_rcv_saddr = iph->daddr; - newinet->inet_saddr = iph->daddr; -#if IS_ENABLED(CONFIG_IPV6) - } else { - struct tcp6_sock *newtcp6sk = (struct tcp6_sock *)newsk; - struct inet_request_sock *treq = inet_rsk(oreq); - struct ipv6_pinfo *newnp = inet6_sk(newsk); - struct ipv6_pinfo *np = inet6_sk(lsk); - - newinet->pinet6 = &newtcp6sk->inet6; - newinet->ipv6_fl_list = NULL; - memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - newsk->sk_v6_daddr = treq->ir_v6_rmt_addr; - newsk->sk_v6_rcv_saddr = treq->ir_v6_loc_addr; - inet6_sk(newsk)->saddr = treq->ir_v6_loc_addr; - newnp->pktoptions = NULL; - newsk->sk_bound_dev_if = treq->ir_iif; - newinet->inet_opt = NULL; - newinet->inet_daddr = LOOPBACK4_IPV6; - newinet->inet_saddr = LOOPBACK4_IPV6; -#endif - } - - oreq->ts_recent = PASS_OPEN_TID_G(ntohl(req->tos_stid)); - sk_setup_caps(newsk, dst); - ctx = tls_get_ctx(lsk); - newsk->sk_destruct = ctx->sk_destruct; - newsk->sk_prot_creator = lsk->sk_prot_creator; - csk->sk = newsk; - csk->passive_reap_next = oreq; - csk->tx_chan = cxgb4_port_chan(ndev); - csk->port_id = port_id; - csk->egress_dev = ndev; - csk->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid)); - chtls_set_tcp_window(csk); - tp->rcv_wnd = csk->rcv_win; - csk->sndbuf = csk->snd_win; - csk->ulp_mode = ULP_MODE_TLS; - step = cdev->lldi->nrxq / cdev->lldi->nchan; - rxq_idx = port_id * step; - rxq_idx += cdev->round_robin_cnt++ % step; - csk->rss_qid = cdev->lldi->rxq_ids[rxq_idx]; - csk->txq_idx = (rxq_idx < cdev->lldi->ntxq) ? rxq_idx : - port_id * step; - csk->sndbuf = newsk->sk_sndbuf; - csk->smac_idx = ((struct port_info *)netdev_priv(ndev))->smt_idx; - RCV_WSCALE(tp) = select_rcv_wscale(tcp_full_space(newsk), - READ_ONCE(sock_net(newsk)-> - ipv4.sysctl_tcp_window_scaling), - tp->window_clamp); - neigh_release(n); - inet_inherit_port(lsk, newsk); - csk_set_flag(csk, CSK_CONN_INLINE); - bh_unlock_sock(newsk); /* tcp_create_openreq_child ->sk_clone_lock */ - - return newsk; -free_csk: - chtls_sock_release(&csk->kref); -free_dst: - if (n) - neigh_release(n); - dst_release(dst); -free_sk: - inet_csk_prepare_forced_close(newsk); - tcp_done(newsk); -free_oreq: - chtls_reqsk_free(oreq); - return NULL; -} - -/* - * Populate a TID_RELEASE WR. The skb must be already propely sized. - */ -static void mk_tid_release(struct sk_buff *skb, - unsigned int chan, unsigned int tid) -{ - struct cpl_tid_release *req; - unsigned int len; - - len = roundup(sizeof(struct cpl_tid_release), 16); - req = (struct cpl_tid_release *)__skb_put(skb, len); - memset(req, 0, len); - set_wr_txq(skb, CPL_PRIORITY_SETUP, chan); - INIT_TP_WR_CPL(req, CPL_TID_RELEASE, tid); -} - -static int chtls_get_module(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - if (!try_module_get(icsk->icsk_ulp_ops->owner)) - return -1; - - return 0; -} - -static void chtls_pass_accept_request(struct sock *sk, - struct sk_buff *skb) -{ - struct cpl_t5_pass_accept_rpl *rpl; - struct cpl_pass_accept_req *req; - struct listen_ctx *listen_ctx; - struct vlan_ethhdr *vlan_eh; - struct request_sock *oreq; - struct sk_buff *reply_skb; - struct chtls_sock *csk; - struct chtls_dev *cdev; - struct ipv6hdr *ip6h; - struct tcphdr *tcph; - struct sock *newsk; - struct ethhdr *eh; - struct iphdr *iph; - void *network_hdr; - unsigned int stid; - unsigned int len; - unsigned int tid; - bool th_ecn, ect; - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ - u16 eth_hdr_len; - bool ecn_ok; - - req = cplhdr(skb) + RSS_HDR; - tid = GET_TID(req); - cdev = BLOG_SKB_CB(skb)->cdev; - newsk = lookup_tid(cdev->tids, tid); - stid = PASS_OPEN_TID_G(ntohl(req->tos_stid)); - if (newsk) { - pr_info("tid (%d) already in use\n", tid); - return; - } - - len = roundup(sizeof(*rpl), 16); - reply_skb = alloc_skb(len, GFP_ATOMIC); - if (!reply_skb) { - cxgb4_remove_tid(cdev->tids, 0, tid, sk->sk_family); - kfree_skb(skb); - return; - } - - if (sk->sk_state != TCP_LISTEN) - goto reject; - - if (inet_csk_reqsk_queue_is_full(sk)) - goto reject; - - if (sk_acceptq_is_full(sk)) - goto reject; - - - eth_hdr_len = T6_ETH_HDR_LEN_G(ntohl(req->hdr_len)); - if (eth_hdr_len == ETH_HLEN) { - eh = (struct ethhdr *)(req + 1); - iph = (struct iphdr *)(eh + 1); - ip6h = (struct ipv6hdr *)(eh + 1); - network_hdr = (void *)(eh + 1); - } else { - vlan_eh = (struct vlan_ethhdr *)(req + 1); - iph = (struct iphdr *)(vlan_eh + 1); - ip6h = (struct ipv6hdr *)(vlan_eh + 1); - network_hdr = (void *)(vlan_eh + 1); - } - - if (iph->version == 0x4) { - tcph = (struct tcphdr *)(iph + 1); - skb_set_network_header(skb, (void *)iph - (void *)req); - oreq = inet_reqsk_alloc(&chtls_rsk_ops, sk, true); - } else { - tcph = (struct tcphdr *)(ip6h + 1); - skb_set_network_header(skb, (void *)ip6h - (void *)req); - oreq = inet_reqsk_alloc(&chtls_rsk_opsv6, sk, false); - } - - if (!oreq) - goto reject; - - oreq->rsk_rcv_wnd = 0; - oreq->rsk_window_clamp = 0; - oreq->syncookie = 0; - oreq->mss = 0; - oreq->ts_recent = 0; - - tcp_rsk(oreq)->tfo_listener = false; - tcp_rsk(oreq)->rcv_isn = ntohl(tcph->seq); - chtls_set_req_port(oreq, tcph->source, tcph->dest); - if (iph->version == 0x4) { - chtls_set_req_addr(oreq, iph->daddr, iph->saddr); - ip_dsfield = ipv4_get_dsfield(iph); -#if IS_ENABLED(CONFIG_IPV6) - } else { - inet_rsk(oreq)->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; - inet_rsk(oreq)->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - ip_dsfield = ipv6_get_dsfield(ipv6_hdr(skb)); -#endif - } - if (req->tcpopt.wsf <= 14 && - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { - inet_rsk(oreq)->wscale_ok = 1; - inet_rsk(oreq)->snd_wscale = req->tcpopt.wsf; - } - inet_rsk(oreq)->ir_iif = sk->sk_bound_dev_if; - th_ecn = tcph->ece && tcph->cwr; - if (th_ecn) { - ect = !INET_ECN_is_not_ect(ip_dsfield); - ecn_ok = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn); - if ((!ect && ecn_ok) || tcp_ca_needs_ecn(sk)) - inet_rsk(oreq)->ecn_ok = 1; - } - - newsk = chtls_recv_sock(sk, oreq, network_hdr, req, cdev); - if (!newsk) - goto reject; - - if (chtls_get_module(newsk)) - goto reject; - inet_csk_reqsk_queue_added(sk); - reply_skb->sk = newsk; - chtls_install_cpl_ops(newsk); - cxgb4_insert_tid(cdev->tids, newsk, tid, newsk->sk_family); - csk = rcu_dereference_sk_user_data(newsk); - listen_ctx = (struct listen_ctx *)lookup_stid(cdev->tids, stid); - csk->listen_ctx = listen_ctx; - __skb_queue_tail(&listen_ctx->synq, (struct sk_buff *)&csk->synq); - chtls_pass_accept_rpl(reply_skb, req, tid); - kfree_skb(skb); - return; - -reject: - mk_tid_release(reply_skb, 0, tid); - cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb); - kfree_skb(skb); -} - -/* - * Handle a CPL_PASS_ACCEPT_REQ message. - */ -static int chtls_pass_accept_req(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_pass_accept_req *req = cplhdr(skb) + RSS_HDR; - struct listen_ctx *ctx; - unsigned int stid; - unsigned int tid; - struct sock *lsk; - void *data; - - stid = PASS_OPEN_TID_G(ntohl(req->tos_stid)); - tid = GET_TID(req); - - data = lookup_stid(cdev->tids, stid); - if (!data) - return 1; - - ctx = (struct listen_ctx *)data; - lsk = ctx->lsk; - - if (unlikely(tid_out_of_range(cdev->tids, tid))) { - pr_info("passive open TID %u too large\n", tid); - return 1; - } - - BLOG_SKB_CB(skb)->cdev = cdev; - process_cpl_msg(chtls_pass_accept_request, lsk, skb); - return 0; -} - -/* - * Completes some final bits of initialization for just established connections - * and changes their state to TCP_ESTABLISHED. - * - * snd_isn here is the ISN after the SYN, i.e., the true ISN + 1. - */ -static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt) -{ - struct tcp_sock *tp = tcp_sk(sk); - - tp->pushed_seq = snd_isn; - tp->write_seq = snd_isn; - tp->snd_nxt = snd_isn; - tp->snd_una = snd_isn; - atomic_set(&inet_sk(sk)->inet_id, get_random_u16()); - assign_rxopt(sk, opt); - - if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10)) - tp->rcv_wup -= tp->rcv_wnd - (RCV_BUFSIZ_M << 10); - - smp_mb(); - tcp_set_state(sk, TCP_ESTABLISHED); -} - -static void chtls_abort_conn(struct sock *sk, struct sk_buff *skb) -{ - struct sk_buff *abort_skb; - - abort_skb = alloc_skb(sizeof(struct cpl_abort_req), GFP_ATOMIC); - if (abort_skb) - chtls_send_reset(sk, CPL_ABORT_SEND_RST, abort_skb); -} - -static struct sock *reap_list; -static DEFINE_SPINLOCK(reap_list_lock); - -/* - * Process the reap list. - */ -DECLARE_TASK_FUNC(process_reap_list, task_param) -{ - spin_lock_bh(&reap_list_lock); - while (reap_list) { - struct sock *sk = reap_list; - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - - reap_list = csk->passive_reap_next; - csk->passive_reap_next = NULL; - spin_unlock(&reap_list_lock); - sock_hold(sk); - - bh_lock_sock(sk); - chtls_abort_conn(sk, NULL); - sock_orphan(sk); - if (sk->sk_state == TCP_CLOSE) - inet_csk_destroy_sock(sk); - bh_unlock_sock(sk); - sock_put(sk); - spin_lock(&reap_list_lock); - } - spin_unlock_bh(&reap_list_lock); -} - -static DECLARE_WORK(reap_task, process_reap_list); - -static void add_to_reap_list(struct sock *sk) -{ - struct chtls_sock *csk = sk->sk_user_data; - - local_bh_disable(); - release_tcp_port(sk); /* release the port immediately */ - - spin_lock(&reap_list_lock); - csk->passive_reap_next = reap_list; - reap_list = sk; - if (!csk->passive_reap_next) - schedule_work(&reap_task); - spin_unlock(&reap_list_lock); - local_bh_enable(); -} - -static void add_pass_open_to_parent(struct sock *child, struct sock *lsk, - struct chtls_dev *cdev) -{ - struct request_sock *oreq; - struct chtls_sock *csk; - - if (lsk->sk_state != TCP_LISTEN) - return; - - csk = child->sk_user_data; - oreq = csk->passive_reap_next; - csk->passive_reap_next = NULL; - - reqsk_queue_removed(&inet_csk(lsk)->icsk_accept_queue, oreq); - __skb_unlink((struct sk_buff *)&csk->synq, &csk->listen_ctx->synq); - - if (sk_acceptq_is_full(lsk)) { - chtls_reqsk_free(oreq); - add_to_reap_list(child); - } else { - refcount_set(&oreq->rsk_refcnt, 1); - inet_csk_reqsk_queue_add(lsk, oreq, child); - lsk->sk_data_ready(lsk); - } -} - -static void bl_add_pass_open_to_parent(struct sock *lsk, struct sk_buff *skb) -{ - struct sock *child = skb->sk; - - skb->sk = NULL; - add_pass_open_to_parent(child, lsk, BLOG_SKB_CB(skb)->cdev); - kfree_skb(skb); -} - -static int chtls_pass_establish(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_pass_establish *req = cplhdr(skb) + RSS_HDR; - struct chtls_sock *csk; - struct sock *lsk, *sk; - unsigned int hwtid; - - hwtid = GET_TID(req); - sk = lookup_tid(cdev->tids, hwtid); - if (!sk) - return (CPL_RET_UNKNOWN_TID | CPL_RET_BUF_DONE); - - bh_lock_sock(sk); - if (unlikely(sock_owned_by_user(sk))) { - kfree_skb(skb); - } else { - unsigned int stid; - void *data; - - csk = sk->sk_user_data; - csk->wr_max_credits = 64; - csk->wr_credits = 64; - csk->wr_unacked = 0; - make_established(sk, ntohl(req->snd_isn), ntohs(req->tcp_opt)); - stid = PASS_OPEN_TID_G(ntohl(req->tos_stid)); - sk->sk_state_change(sk); - if (unlikely(sk->sk_socket)) - sk_wake_async(sk, 0, POLL_OUT); - - data = lookup_stid(cdev->tids, stid); - if (!data) { - /* listening server close */ - kfree_skb(skb); - goto unlock; - } - lsk = ((struct listen_ctx *)data)->lsk; - - bh_lock_sock(lsk); - if (unlikely(skb_queue_empty(&csk->listen_ctx->synq))) { - /* removed from synq */ - bh_unlock_sock(lsk); - kfree_skb(skb); - goto unlock; - } - - if (likely(!sock_owned_by_user(lsk))) { - kfree_skb(skb); - add_pass_open_to_parent(sk, lsk, cdev); - } else { - skb->sk = sk; - BLOG_SKB_CB(skb)->cdev = cdev; - BLOG_SKB_CB(skb)->backlog_rcv = - bl_add_pass_open_to_parent; - __sk_add_backlog(lsk, skb); - } - bh_unlock_sock(lsk); - } -unlock: - bh_unlock_sock(sk); - return 0; -} - -/* - * Handle receipt of an urgent pointer. - */ -static void handle_urg_ptr(struct sock *sk, u32 urg_seq) -{ - struct tcp_sock *tp = tcp_sk(sk); - - urg_seq--; - if (tp->urg_data && !after(urg_seq, tp->urg_seq)) - return; /* duplicate pointer */ - - sk_send_sigurg(sk); - if (tp->urg_seq == tp->copied_seq && tp->urg_data && - !sock_flag(sk, SOCK_URGINLINE) && - tp->copied_seq != tp->rcv_nxt) { - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); - - tp->copied_seq++; - if (skb && tp->copied_seq - ULP_SKB_CB(skb)->seq >= skb->len) - chtls_free_skb(sk, skb); - } - - tp->urg_data = TCP_URG_NOTYET; - tp->urg_seq = urg_seq; -} - -static void check_sk_callbacks(struct chtls_sock *csk) -{ - struct sock *sk = csk->sk; - - if (unlikely(sk->sk_user_data && - !csk_flag_nochk(csk, CSK_CALLBACKS_CHKD))) - csk_set_flag(csk, CSK_CALLBACKS_CHKD); -} - -/* - * Handles Rx data that arrives in a state where the socket isn't accepting - * new data. - */ -static void handle_excess_rx(struct sock *sk, struct sk_buff *skb) -{ - if (!csk_flag(sk, CSK_ABORT_SHUTDOWN)) - chtls_abort_conn(sk, skb); - - kfree_skb(skb); -} - -static void chtls_recv_data(struct sock *sk, struct sk_buff *skb) -{ - struct cpl_rx_data *hdr = cplhdr(skb) + RSS_HDR; - struct chtls_sock *csk; - struct tcp_sock *tp; - - csk = rcu_dereference_sk_user_data(sk); - tp = tcp_sk(sk); - - if (unlikely(sk->sk_shutdown & RCV_SHUTDOWN)) { - handle_excess_rx(sk, skb); - return; - } - - ULP_SKB_CB(skb)->seq = ntohl(hdr->seq); - ULP_SKB_CB(skb)->psh = hdr->psh; - skb_ulp_mode(skb) = ULP_MODE_NONE; - - skb_reset_transport_header(skb); - __skb_pull(skb, sizeof(*hdr) + RSS_HDR); - if (!skb->data_len) - __skb_trim(skb, ntohs(hdr->len)); - - if (unlikely(hdr->urg)) - handle_urg_ptr(sk, tp->rcv_nxt + ntohs(hdr->urg)); - if (unlikely(tp->urg_data == TCP_URG_NOTYET && - tp->urg_seq - tp->rcv_nxt < skb->len)) - tp->urg_data = TCP_URG_VALID | - skb->data[tp->urg_seq - tp->rcv_nxt]; - - if (unlikely(hdr->dack_mode != csk->delack_mode)) { - csk->delack_mode = hdr->dack_mode; - csk->delack_seq = tp->rcv_nxt; - } - - tcp_hdr(skb)->fin = 0; - tp->rcv_nxt += skb->len; - - __skb_queue_tail(&sk->sk_receive_queue, skb); - - if (!sock_flag(sk, SOCK_DEAD)) { - check_sk_callbacks(csk); - sk->sk_data_ready(sk); - } -} - -static int chtls_rx_data(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_rx_data *req = cplhdr(skb) + RSS_HDR; - unsigned int hwtid = GET_TID(req); - struct sock *sk; - - sk = lookup_tid(cdev->tids, hwtid); - if (unlikely(!sk)) { - pr_err("can't find conn. for hwtid %u.\n", hwtid); - return -EINVAL; - } - skb_dstref_steal(skb); - process_cpl_msg(chtls_recv_data, sk, skb); - return 0; -} - -static void chtls_recv_pdu(struct sock *sk, struct sk_buff *skb) -{ - struct cpl_tls_data *hdr = cplhdr(skb); - struct chtls_sock *csk; - struct chtls_hws *tlsk; - struct tcp_sock *tp; - - csk = rcu_dereference_sk_user_data(sk); - tlsk = &csk->tlshws; - tp = tcp_sk(sk); - - if (unlikely(sk->sk_shutdown & RCV_SHUTDOWN)) { - handle_excess_rx(sk, skb); - return; - } - - ULP_SKB_CB(skb)->seq = ntohl(hdr->seq); - ULP_SKB_CB(skb)->flags = 0; - skb_ulp_mode(skb) = ULP_MODE_TLS; - - skb_reset_transport_header(skb); - __skb_pull(skb, sizeof(*hdr)); - if (!skb->data_len) - __skb_trim(skb, - CPL_TLS_DATA_LENGTH_G(ntohl(hdr->length_pkd))); - - if (unlikely(tp->urg_data == TCP_URG_NOTYET && tp->urg_seq - - tp->rcv_nxt < skb->len)) - tp->urg_data = TCP_URG_VALID | - skb->data[tp->urg_seq - tp->rcv_nxt]; - - tcp_hdr(skb)->fin = 0; - tlsk->pldlen = CPL_TLS_DATA_LENGTH_G(ntohl(hdr->length_pkd)); - __skb_queue_tail(&tlsk->sk_recv_queue, skb); -} - -static int chtls_rx_pdu(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_tls_data *req = cplhdr(skb); - unsigned int hwtid = GET_TID(req); - struct sock *sk; - - sk = lookup_tid(cdev->tids, hwtid); - if (unlikely(!sk)) { - pr_err("can't find conn. for hwtid %u.\n", hwtid); - return -EINVAL; - } - skb_dstref_steal(skb); - process_cpl_msg(chtls_recv_pdu, sk, skb); - return 0; -} - -static void chtls_set_hdrlen(struct sk_buff *skb, unsigned int nlen) -{ - struct tlsrx_cmp_hdr *tls_cmp_hdr = cplhdr(skb); - - skb->hdr_len = ntohs((__force __be16)tls_cmp_hdr->length); - tls_cmp_hdr->length = ntohs((__force __be16)nlen); -} - -static void chtls_rx_hdr(struct sock *sk, struct sk_buff *skb) -{ - struct tlsrx_cmp_hdr *tls_hdr_pkt; - struct cpl_rx_tls_cmp *cmp_cpl; - struct sk_buff *skb_rec; - struct chtls_sock *csk; - struct chtls_hws *tlsk; - struct tcp_sock *tp; - - cmp_cpl = cplhdr(skb); - csk = rcu_dereference_sk_user_data(sk); - tlsk = &csk->tlshws; - tp = tcp_sk(sk); - - ULP_SKB_CB(skb)->seq = ntohl(cmp_cpl->seq); - ULP_SKB_CB(skb)->flags = 0; - - skb_reset_transport_header(skb); - __skb_pull(skb, sizeof(*cmp_cpl)); - tls_hdr_pkt = (struct tlsrx_cmp_hdr *)skb->data; - if (tls_hdr_pkt->res_to_mac_error & TLSRX_HDR_PKT_ERROR_M) - tls_hdr_pkt->type = CONTENT_TYPE_ERROR; - if (!skb->data_len) - __skb_trim(skb, TLS_HEADER_LENGTH); - - tp->rcv_nxt += - CPL_RX_TLS_CMP_PDULENGTH_G(ntohl(cmp_cpl->pdulength_length)); - - ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_TLS_HDR; - skb_rec = __skb_dequeue(&tlsk->sk_recv_queue); - if (!skb_rec) { - __skb_queue_tail(&sk->sk_receive_queue, skb); - } else { - chtls_set_hdrlen(skb, tlsk->pldlen); - tlsk->pldlen = 0; - __skb_queue_tail(&sk->sk_receive_queue, skb); - __skb_queue_tail(&sk->sk_receive_queue, skb_rec); - } - - if (!sock_flag(sk, SOCK_DEAD)) { - check_sk_callbacks(csk); - sk->sk_data_ready(sk); - } -} - -static int chtls_rx_cmp(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_rx_tls_cmp *req = cplhdr(skb); - unsigned int hwtid = GET_TID(req); - struct sock *sk; - - sk = lookup_tid(cdev->tids, hwtid); - if (unlikely(!sk)) { - pr_err("can't find conn. for hwtid %u.\n", hwtid); - return -EINVAL; - } - skb_dstref_steal(skb); - process_cpl_msg(chtls_rx_hdr, sk, skb); - - return 0; -} - -static void chtls_timewait(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - tp->rcv_nxt++; - tp->rx_opt.ts_recent_stamp = ktime_get_seconds(); - tp->srtt_us = 0; - tcp_time_wait(sk, TCP_TIME_WAIT, 0); -} - -static void chtls_peer_close(struct sock *sk, struct sk_buff *skb) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - - if (csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) - goto out; - - sk->sk_shutdown |= RCV_SHUTDOWN; - sock_set_flag(sk, SOCK_DONE); - - switch (sk->sk_state) { - case TCP_SYN_RECV: - case TCP_ESTABLISHED: - tcp_set_state(sk, TCP_CLOSE_WAIT); - break; - case TCP_FIN_WAIT1: - tcp_set_state(sk, TCP_CLOSING); - break; - case TCP_FIN_WAIT2: - chtls_release_resources(sk); - if (csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) - chtls_conn_done(sk); - else - chtls_timewait(sk); - break; - default: - pr_info("cpl_peer_close in bad state %d\n", sk->sk_state); - } - - if (!sock_flag(sk, SOCK_DEAD)) { - sk->sk_state_change(sk); - /* Do not send POLL_HUP for half duplex close. */ - - if ((sk->sk_shutdown & SEND_SHUTDOWN) || - sk->sk_state == TCP_CLOSE) - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); - else - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); - } -out: - kfree_skb(skb); -} - -static void chtls_close_con_rpl(struct sock *sk, struct sk_buff *skb) -{ - struct cpl_close_con_rpl *rpl = cplhdr(skb) + RSS_HDR; - struct chtls_sock *csk; - struct tcp_sock *tp; - - csk = rcu_dereference_sk_user_data(sk); - - if (csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) - goto out; - - tp = tcp_sk(sk); - - tp->snd_una = ntohl(rpl->snd_nxt) - 1; /* exclude FIN */ - - switch (sk->sk_state) { - case TCP_CLOSING: - chtls_release_resources(sk); - if (csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) - chtls_conn_done(sk); - else - chtls_timewait(sk); - break; - case TCP_LAST_ACK: - chtls_release_resources(sk); - chtls_conn_done(sk); - break; - case TCP_FIN_WAIT1: - tcp_set_state(sk, TCP_FIN_WAIT2); - sk->sk_shutdown |= SEND_SHUTDOWN; - - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - else if (tcp_sk(sk)->linger2 < 0 && - !csk_flag_nochk(csk, CSK_ABORT_SHUTDOWN)) - chtls_abort_conn(sk, skb); - else if (csk_flag_nochk(csk, CSK_TX_DATA_SENT)) - chtls_set_quiesce_ctrl(sk, 0); - break; - default: - pr_info("close_con_rpl in bad state %d\n", sk->sk_state); - } -out: - kfree_skb(skb); -} - -static struct sk_buff *get_cpl_skb(struct sk_buff *skb, - size_t len, gfp_t gfp) -{ - if (likely(!skb_is_nonlinear(skb) && !skb_cloned(skb))) { - WARN_ONCE(skb->len < len, "skb alloc error"); - __skb_trim(skb, len); - skb_get(skb); - } else { - skb = alloc_skb(len, gfp); - if (skb) - __skb_put(skb, len); - } - return skb; -} - -static void set_abort_rpl_wr(struct sk_buff *skb, unsigned int tid, - int cmd) -{ - struct cpl_abort_rpl *rpl = cplhdr(skb); - - INIT_TP_WR_CPL(rpl, CPL_ABORT_RPL, tid); - rpl->cmd = cmd; -} - -static void send_defer_abort_rpl(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_abort_req_rss *req = cplhdr(skb); - struct sk_buff *reply_skb; - - reply_skb = alloc_skb(sizeof(struct cpl_abort_rpl), - GFP_KERNEL | __GFP_NOFAIL); - __skb_put(reply_skb, sizeof(struct cpl_abort_rpl)); - set_abort_rpl_wr(reply_skb, GET_TID(req), - (req->status & CPL_ABORT_NO_RST)); - set_wr_txq(reply_skb, CPL_PRIORITY_DATA, req->status >> 1); - cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb); - kfree_skb(skb); -} - -/* - * Add an skb to the deferred skb queue for processing from process context. - */ -static void t4_defer_reply(struct sk_buff *skb, struct chtls_dev *cdev, - defer_handler_t handler) -{ - DEFERRED_SKB_CB(skb)->handler = handler; - spin_lock_bh(&cdev->deferq.lock); - __skb_queue_tail(&cdev->deferq, skb); - if (skb_queue_len(&cdev->deferq) == 1) - schedule_work(&cdev->deferq_task); - spin_unlock_bh(&cdev->deferq.lock); -} - -static void chtls_send_abort_rpl(struct sock *sk, struct sk_buff *skb, - struct chtls_dev *cdev, - int status, int queue) -{ - struct cpl_abort_req_rss *req = cplhdr(skb) + RSS_HDR; - struct sk_buff *reply_skb; - struct chtls_sock *csk; - unsigned int tid; - - csk = rcu_dereference_sk_user_data(sk); - tid = GET_TID(req); - - reply_skb = get_cpl_skb(skb, sizeof(struct cpl_abort_rpl), gfp_any()); - if (!reply_skb) { - req->status = (queue << 1) | status; - t4_defer_reply(skb, cdev, send_defer_abort_rpl); - return; - } - - set_abort_rpl_wr(reply_skb, tid, status); - kfree_skb(skb); - set_wr_txq(reply_skb, CPL_PRIORITY_DATA, queue); - if (csk_conn_inline(csk)) { - struct l2t_entry *e = csk->l2t_entry; - - if (e && sk->sk_state != TCP_SYN_RECV) { - cxgb4_l2t_send(csk->egress_dev, reply_skb, e); - return; - } - } - cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb); -} - -/* - * This is run from a listener's backlog to abort a child connection in - * SYN_RCV state (i.e., one on the listener's SYN queue). - */ -static void bl_abort_syn_rcv(struct sock *lsk, struct sk_buff *skb) -{ - struct chtls_sock *csk; - struct sock *child; - int queue; - - child = skb->sk; - csk = rcu_dereference_sk_user_data(child); - queue = csk->txq_idx; - - skb->sk = NULL; - chtls_send_abort_rpl(child, skb, BLOG_SKB_CB(skb)->cdev, - CPL_ABORT_NO_RST, queue); - do_abort_syn_rcv(child, lsk); -} - -static int abort_syn_rcv(struct sock *sk, struct sk_buff *skb) -{ - const struct request_sock *oreq; - struct listen_ctx *listen_ctx; - struct chtls_sock *csk; - struct chtls_dev *cdev; - struct sock *psk; - void *ctx; - - csk = sk->sk_user_data; - oreq = csk->passive_reap_next; - cdev = csk->cdev; - - if (!oreq) - return -1; - - ctx = lookup_stid(cdev->tids, oreq->ts_recent); - if (!ctx) - return -1; - - listen_ctx = (struct listen_ctx *)ctx; - psk = listen_ctx->lsk; - - bh_lock_sock(psk); - if (!sock_owned_by_user(psk)) { - int queue = csk->txq_idx; - - chtls_send_abort_rpl(sk, skb, cdev, CPL_ABORT_NO_RST, queue); - do_abort_syn_rcv(sk, psk); - } else { - skb->sk = sk; - BLOG_SKB_CB(skb)->backlog_rcv = bl_abort_syn_rcv; - __sk_add_backlog(psk, skb); - } - bh_unlock_sock(psk); - return 0; -} - -static void chtls_abort_req_rss(struct sock *sk, struct sk_buff *skb) -{ - const struct cpl_abort_req_rss *req = cplhdr(skb) + RSS_HDR; - struct chtls_sock *csk = sk->sk_user_data; - int rst_status = CPL_ABORT_NO_RST; - int queue = csk->txq_idx; - - if (is_neg_adv(req->status)) { - kfree_skb(skb); - return; - } - - csk_reset_flag(csk, CSK_ABORT_REQ_RCVD); - - if (!csk_flag_nochk(csk, CSK_ABORT_SHUTDOWN) && - !csk_flag_nochk(csk, CSK_TX_DATA_SENT)) { - struct tcp_sock *tp = tcp_sk(sk); - - if (send_tx_flowc_wr(sk, 0, tp->snd_nxt, tp->rcv_nxt) < 0) - WARN_ONCE(1, "send_tx_flowc error"); - csk_set_flag(csk, CSK_TX_DATA_SENT); - } - - csk_set_flag(csk, CSK_ABORT_SHUTDOWN); - - if (!csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) { - sk->sk_err = ETIMEDOUT; - - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); - - if (sk->sk_state == TCP_SYN_RECV && !abort_syn_rcv(sk, skb)) - return; - - } - - chtls_send_abort_rpl(sk, skb, BLOG_SKB_CB(skb)->cdev, - rst_status, queue); - chtls_release_resources(sk); - chtls_conn_done(sk); -} - -static void chtls_abort_rpl_rss(struct sock *sk, struct sk_buff *skb) -{ - struct cpl_abort_rpl_rss *rpl = cplhdr(skb) + RSS_HDR; - struct chtls_sock *csk; - struct chtls_dev *cdev; - - csk = rcu_dereference_sk_user_data(sk); - cdev = csk->cdev; - - if (csk_flag_nochk(csk, CSK_ABORT_RPL_PENDING)) { - csk_reset_flag(csk, CSK_ABORT_RPL_PENDING); - if (!csk_flag_nochk(csk, CSK_ABORT_REQ_RCVD)) { - if (sk->sk_state == TCP_SYN_SENT) { - cxgb4_remove_tid(cdev->tids, - csk->port_id, - GET_TID(rpl), - sk->sk_family); - sock_put(sk); - } - chtls_release_resources(sk); - chtls_conn_done(sk); - } - } - kfree_skb(skb); -} - -static int chtls_conn_cpl(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_peer_close *req = cplhdr(skb) + RSS_HDR; - void (*fn)(struct sock *sk, struct sk_buff *skb); - unsigned int hwtid = GET_TID(req); - struct chtls_sock *csk; - struct sock *sk; - u8 opcode; - - opcode = ((const struct rss_header *)cplhdr(skb))->opcode; - - sk = lookup_tid(cdev->tids, hwtid); - if (!sk) - goto rel_skb; - - csk = sk->sk_user_data; - - switch (opcode) { - case CPL_PEER_CLOSE: - fn = chtls_peer_close; - break; - case CPL_CLOSE_CON_RPL: - fn = chtls_close_con_rpl; - break; - case CPL_ABORT_REQ_RSS: - /* - * Save the offload device in the skb, we may process this - * message after the socket has closed. - */ - BLOG_SKB_CB(skb)->cdev = csk->cdev; - fn = chtls_abort_req_rss; - break; - case CPL_ABORT_RPL_RSS: - fn = chtls_abort_rpl_rss; - break; - default: - goto rel_skb; - } - - process_cpl_msg(fn, sk, skb); - return 0; - -rel_skb: - kfree_skb(skb); - return 0; -} - -static void chtls_rx_ack(struct sock *sk, struct sk_buff *skb) -{ - struct cpl_fw4_ack *hdr = cplhdr(skb) + RSS_HDR; - struct chtls_sock *csk = sk->sk_user_data; - struct tcp_sock *tp = tcp_sk(sk); - u32 credits = hdr->credits; - u32 snd_una; - - snd_una = ntohl(hdr->snd_una); - csk->wr_credits += credits; - - if (csk->wr_unacked > csk->wr_max_credits - csk->wr_credits) - csk->wr_unacked = csk->wr_max_credits - csk->wr_credits; - - while (credits) { - struct sk_buff *pskb = csk->wr_skb_head; - u32 csum; - - if (unlikely(!pskb)) { - if (csk->wr_nondata) - csk->wr_nondata -= credits; - break; - } - csum = (__force u32)pskb->csum; - if (unlikely(credits < csum)) { - pskb->csum = (__force __wsum)(csum - credits); - break; - } - dequeue_wr(sk); - credits -= csum; - kfree_skb(pskb); - } - if (hdr->seq_vld & CPL_FW4_ACK_FLAGS_SEQVAL) { - if (unlikely(before(snd_una, tp->snd_una))) { - kfree_skb(skb); - return; - } - - if (tp->snd_una != snd_una) { - tp->snd_una = snd_una; - tp->rcv_tstamp = tcp_jiffies32; - if (tp->snd_una == tp->snd_nxt && - !csk_flag_nochk(csk, CSK_TX_FAILOVER)) - csk_reset_flag(csk, CSK_TX_WAIT_IDLE); - } - } - - if (hdr->seq_vld & CPL_FW4_ACK_FLAGS_CH) { - unsigned int fclen16 = roundup(failover_flowc_wr_len, 16); - - csk->wr_credits -= fclen16; - csk_reset_flag(csk, CSK_TX_WAIT_IDLE); - csk_reset_flag(csk, CSK_TX_FAILOVER); - } - if (skb_queue_len(&csk->txq) && chtls_push_frames(csk, 0)) - sk->sk_write_space(sk); - - kfree_skb(skb); -} - -static int chtls_wr_ack(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_fw4_ack *rpl = cplhdr(skb) + RSS_HDR; - unsigned int hwtid = GET_TID(rpl); - struct sock *sk; - - sk = lookup_tid(cdev->tids, hwtid); - if (unlikely(!sk)) { - pr_err("can't find conn. for hwtid %u.\n", hwtid); - return -EINVAL; - } - process_cpl_msg(chtls_rx_ack, sk, skb); - - return 0; -} - -static int chtls_set_tcb_rpl(struct chtls_dev *cdev, struct sk_buff *skb) -{ - struct cpl_set_tcb_rpl *rpl = cplhdr(skb) + RSS_HDR; - unsigned int hwtid = GET_TID(rpl); - struct sock *sk; - - sk = lookup_tid(cdev->tids, hwtid); - - /* return EINVAL if socket doesn't exist */ - if (!sk) - return -EINVAL; - - /* Reusing the skb as size of cpl_set_tcb_field structure - * is greater than cpl_abort_req - */ - if (TCB_COOKIE_G(rpl->cookie) == TCB_FIELD_COOKIE_TFLAG) - chtls_send_abort(sk, CPL_ABORT_SEND_RST, NULL); - - kfree_skb(skb); - return 0; -} - -chtls_handler_func chtls_handlers[NUM_CPL_CMDS] = { - [CPL_PASS_OPEN_RPL] = chtls_pass_open_rpl, - [CPL_CLOSE_LISTSRV_RPL] = chtls_close_listsrv_rpl, - [CPL_PASS_ACCEPT_REQ] = chtls_pass_accept_req, - [CPL_PASS_ESTABLISH] = chtls_pass_establish, - [CPL_RX_DATA] = chtls_rx_data, - [CPL_TLS_DATA] = chtls_rx_pdu, - [CPL_RX_TLS_CMP] = chtls_rx_cmp, - [CPL_PEER_CLOSE] = chtls_conn_cpl, - [CPL_CLOSE_CON_RPL] = chtls_conn_cpl, - [CPL_ABORT_REQ_RSS] = chtls_conn_cpl, - [CPL_ABORT_RPL_RSS] = chtls_conn_cpl, - [CPL_FW4_ACK] = chtls_wr_ack, - [CPL_SET_TCB_RPL] = chtls_set_tcb_rpl, -}; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h deleted file mode 100644 index 29ceff5a5fcb..000000000000 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h +++ /dev/null @@ -1,218 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (c) 2018 Chelsio Communications, Inc. - */ - -#ifndef __CHTLS_CM_H__ -#define __CHTLS_CM_H__ - -/* - * TCB settings - */ -/* 3:0 */ -#define TCB_ULP_TYPE_W 0 -#define TCB_ULP_TYPE_S 0 -#define TCB_ULP_TYPE_M 0xfULL -#define TCB_ULP_TYPE_V(x) ((x) << TCB_ULP_TYPE_S) - -/* 11:4 */ -#define TCB_ULP_RAW_W 0 -#define TCB_ULP_RAW_S 4 -#define TCB_ULP_RAW_M 0xffULL -#define TCB_ULP_RAW_V(x) ((x) << TCB_ULP_RAW_S) - -#define TF_TLS_KEY_SIZE_S 7 -#define TF_TLS_KEY_SIZE_V(x) ((x) << TF_TLS_KEY_SIZE_S) - -#define TF_TLS_CONTROL_S 2 -#define TF_TLS_CONTROL_V(x) ((x) << TF_TLS_CONTROL_S) - -#define TF_TLS_ACTIVE_S 1 -#define TF_TLS_ACTIVE_V(x) ((x) << TF_TLS_ACTIVE_S) - -#define TF_TLS_ENABLE_S 0 -#define TF_TLS_ENABLE_V(x) ((x) << TF_TLS_ENABLE_S) - -#define TF_RX_QUIESCE_S 15 -#define TF_RX_QUIESCE_V(x) ((x) << TF_RX_QUIESCE_S) - -/* - * Max receive window supported by HW in bytes. Only a small part of it can - * be set through option0, the rest needs to be set through RX_DATA_ACK. - */ -#define MAX_RCV_WND ((1U << 27) - 1) -#define MAX_MSS 65536 - -/* - * Min receive window. We want it to be large enough to accommodate receive - * coalescing, handle jumbo frames, and not trigger sender SWS avoidance. - */ -#define MIN_RCV_WND (24 * 1024U) -#define LOOPBACK(x) (((x) & htonl(0xff000000)) == htonl(0x7f000000)) - -/* for TX: a skb must have a headroom of at least TX_HEADER_LEN bytes */ -#define TX_HEADER_LEN \ - (sizeof(struct fw_ofld_tx_data_wr) + sizeof(struct sge_opaque_hdr)) -#define TX_TLSHDR_LEN \ - (sizeof(struct fw_tlstx_data_wr) + sizeof(struct cpl_tx_tls_sfo) + \ - sizeof(struct sge_opaque_hdr)) -#define TXDATA_SKB_LEN 128 - -enum { - CPL_TX_TLS_SFO_TYPE_CCS, - CPL_TX_TLS_SFO_TYPE_ALERT, - CPL_TX_TLS_SFO_TYPE_HANDSHAKE, - CPL_TX_TLS_SFO_TYPE_DATA, - CPL_TX_TLS_SFO_TYPE_HEARTBEAT, -}; - -enum { - TLS_HDR_TYPE_CCS = 20, - TLS_HDR_TYPE_ALERT, - TLS_HDR_TYPE_HANDSHAKE, - TLS_HDR_TYPE_RECORD, - TLS_HDR_TYPE_HEARTBEAT, -}; - -typedef void (*defer_handler_t)(struct chtls_dev *dev, struct sk_buff *skb); -extern struct request_sock_ops chtls_rsk_ops; -extern struct request_sock_ops chtls_rsk_opsv6; - -struct deferred_skb_cb { - defer_handler_t handler; - struct chtls_dev *dev; -}; - -#define DEFERRED_SKB_CB(skb) ((struct deferred_skb_cb *)(skb)->cb) -#define failover_flowc_wr_len offsetof(struct fw_flowc_wr, mnemval[3]) -#define WR_SKB_CB(skb) ((struct wr_skb_cb *)(skb)->cb) -#define ACCEPT_QUEUE(sk) (&inet_csk(sk)->icsk_accept_queue.rskq_accept_head) - -#define SND_WSCALE(tp) ((tp)->rx_opt.snd_wscale) -#define RCV_WSCALE(tp) ((tp)->rx_opt.rcv_wscale) -#define USER_MSS(tp) (READ_ONCE((tp)->rx_opt.user_mss)) -#define TS_RECENT_STAMP(tp) ((tp)->rx_opt.ts_recent_stamp) -#define WSCALE_OK(tp) ((tp)->rx_opt.wscale_ok) -#define TSTAMP_OK(tp) ((tp)->rx_opt.tstamp_ok) -#define SACK_OK(tp) ((tp)->rx_opt.sack_ok) - -/* TLS SKB */ -#define skb_ulp_tls_inline(skb) (ULP_SKB_CB(skb)->ulp.tls.ofld) -#define skb_ulp_tls_iv_imm(skb) (ULP_SKB_CB(skb)->ulp.tls.iv) - -void chtls_defer_reply(struct sk_buff *skb, struct chtls_dev *dev, - defer_handler_t handler); - -/* - * Returns true if the socket is in one of the supplied states. - */ -static inline unsigned int sk_in_state(const struct sock *sk, - unsigned int states) -{ - return states & (1 << sk->sk_state); -} - -static void chtls_rsk_destructor(struct request_sock *req) -{ - /* do nothing */ -} - -static inline void chtls_init_rsk_ops(struct proto *chtls_tcp_prot, - struct request_sock_ops *chtls_tcp_ops, - struct proto *tcp_prot, int family) -{ - memset(chtls_tcp_ops, 0, sizeof(*chtls_tcp_ops)); - chtls_tcp_ops->family = family; - chtls_tcp_ops->obj_size = sizeof(struct tcp_request_sock); - chtls_tcp_ops->destructor = chtls_rsk_destructor; - chtls_tcp_ops->slab = tcp_prot->rsk_prot->slab; - chtls_tcp_prot->rsk_prot = chtls_tcp_ops; -} - -static inline void chtls_reqsk_free(struct request_sock *req) -{ - if (req->rsk_listener) - sock_put(req->rsk_listener); - kmem_cache_free(req->rsk_ops->slab, req); -} - -#define DECLARE_TASK_FUNC(task, task_param) \ - static void task(struct work_struct *task_param) - -static inline void sk_wakeup_sleepers(struct sock *sk, bool interruptable) -{ - struct socket_wq *wq; - - rcu_read_lock(); - wq = rcu_dereference(sk->sk_wq); - if (skwq_has_sleeper(wq)) { - if (interruptable) - wake_up_interruptible(sk_sleep(sk)); - else - wake_up_all(sk_sleep(sk)); - } - rcu_read_unlock(); -} - -static inline void chtls_set_req_port(struct request_sock *oreq, - __be16 source, __be16 dest) -{ - inet_rsk(oreq)->ir_rmt_port = source; - inet_rsk(oreq)->ir_num = ntohs(dest); -} - -static inline void chtls_set_req_addr(struct request_sock *oreq, - __be32 local_ip, __be32 peer_ip) -{ - inet_rsk(oreq)->ir_loc_addr = local_ip; - inet_rsk(oreq)->ir_rmt_addr = peer_ip; -} - -static inline void chtls_free_skb(struct sock *sk, struct sk_buff *skb) -{ - skb_dstref_steal(skb); - __skb_unlink(skb, &sk->sk_receive_queue); - __kfree_skb(skb); -} - -static inline void chtls_kfree_skb(struct sock *sk, struct sk_buff *skb) -{ - skb_dstref_steal(skb); - __skb_unlink(skb, &sk->sk_receive_queue); - kfree_skb(skb); -} - -static inline void chtls_reset_wr_list(struct chtls_sock *csk) -{ - csk->wr_skb_head = NULL; - csk->wr_skb_tail = NULL; -} - -static inline void enqueue_wr(struct chtls_sock *csk, struct sk_buff *skb) -{ - WR_SKB_CB(skb)->next_wr = NULL; - - skb_get(skb); - - if (!csk->wr_skb_head) - csk->wr_skb_head = skb; - else - WR_SKB_CB(csk->wr_skb_tail)->next_wr = skb; - csk->wr_skb_tail = skb; -} - -static inline struct sk_buff *dequeue_wr(struct sock *sk) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct sk_buff *skb = NULL; - - skb = csk->wr_skb_head; - - if (likely(skb)) { - /* Don't bother clearing the tail */ - csk->wr_skb_head = WR_SKB_CB(skb)->next_wr; - WR_SKB_CB(skb)->next_wr = NULL; - } - return skb; -} -#endif diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c deleted file mode 100644 index d84473ca844d..000000000000 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c +++ /dev/null @@ -1,462 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2018 Chelsio Communications, Inc. - * - * Written by: Atul Gupta (atul.gupta@chelsio.com) - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "chtls.h" -#include "chtls_cm.h" - -static void __set_tcb_field_direct(struct chtls_sock *csk, - struct cpl_set_tcb_field *req, u16 word, - u64 mask, u64 val, u8 cookie, int no_reply) -{ - struct ulptx_idata *sc; - - INIT_TP_WR_CPL(req, CPL_SET_TCB_FIELD, csk->tid); - req->wr.wr_mid |= htonl(FW_WR_FLOWID_V(csk->tid)); - req->reply_ctrl = htons(NO_REPLY_V(no_reply) | - QUEUENO_V(csk->rss_qid)); - req->word_cookie = htons(TCB_WORD_V(word) | TCB_COOKIE_V(cookie)); - req->mask = cpu_to_be64(mask); - req->val = cpu_to_be64(val); - sc = (struct ulptx_idata *)(req + 1); - sc->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP)); - sc->len = htonl(0); -} - -static void __set_tcb_field(struct sock *sk, struct sk_buff *skb, u16 word, - u64 mask, u64 val, u8 cookie, int no_reply) -{ - struct cpl_set_tcb_field *req; - struct chtls_sock *csk; - struct ulptx_idata *sc; - unsigned int wrlen; - - wrlen = roundup(sizeof(*req) + sizeof(*sc), 16); - csk = rcu_dereference_sk_user_data(sk); - - req = (struct cpl_set_tcb_field *)__skb_put(skb, wrlen); - __set_tcb_field_direct(csk, req, word, mask, val, cookie, no_reply); - set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id); -} - -/* - * Send control message to HW, message go as immediate data and packet - * is freed immediately. - */ -static int chtls_set_tcb_field(struct sock *sk, u16 word, u64 mask, u64 val) -{ - struct cpl_set_tcb_field *req; - unsigned int credits_needed; - struct chtls_sock *csk; - struct ulptx_idata *sc; - struct sk_buff *skb; - unsigned int wrlen; - int ret; - - wrlen = roundup(sizeof(*req) + sizeof(*sc), 16); - - skb = alloc_skb(wrlen, GFP_ATOMIC); - if (!skb) - return -ENOMEM; - - credits_needed = DIV_ROUND_UP(wrlen, 16); - csk = rcu_dereference_sk_user_data(sk); - - __set_tcb_field(sk, skb, word, mask, val, 0, 1); - skb_set_queue_mapping(skb, (csk->txq_idx << 1) | CPL_PRIORITY_DATA); - csk->wr_credits -= credits_needed; - csk->wr_unacked += credits_needed; - enqueue_wr(csk, skb); - ret = cxgb4_ofld_send(csk->egress_dev, skb); - if (ret < 0) - kfree_skb(skb); - return ret < 0 ? ret : 0; -} - -void chtls_set_tcb_field_rpl_skb(struct sock *sk, u16 word, - u64 mask, u64 val, u8 cookie, - int through_l2t) -{ - struct sk_buff *skb; - unsigned int wrlen; - - wrlen = sizeof(struct cpl_set_tcb_field) + sizeof(struct ulptx_idata); - wrlen = roundup(wrlen, 16); - - skb = alloc_skb(wrlen, GFP_KERNEL | __GFP_NOFAIL); - if (!skb) - return; - - __set_tcb_field(sk, skb, word, mask, val, cookie, 0); - send_or_defer(sk, tcp_sk(sk), skb, through_l2t); -} - -static int chtls_set_tcb_keyid(struct sock *sk, int keyid) -{ - return chtls_set_tcb_field(sk, 31, 0xFFFFFFFFULL, keyid); -} - -static int chtls_set_tcb_seqno(struct sock *sk) -{ - return chtls_set_tcb_field(sk, 28, ~0ULL, 0); -} - -static int chtls_set_tcb_quiesce(struct sock *sk, int val) -{ - return chtls_set_tcb_field(sk, 1, (1ULL << TF_RX_QUIESCE_S), - TF_RX_QUIESCE_V(val)); -} - -void chtls_set_quiesce_ctrl(struct sock *sk, int val) -{ - struct chtls_sock *csk; - struct sk_buff *skb; - unsigned int wrlen; - int ret; - - wrlen = sizeof(struct cpl_set_tcb_field) + sizeof(struct ulptx_idata); - wrlen = roundup(wrlen, 16); - - skb = alloc_skb(wrlen, GFP_ATOMIC); - if (!skb) - return; - - csk = rcu_dereference_sk_user_data(sk); - - __set_tcb_field(sk, skb, 1, TF_RX_QUIESCE_V(1), 0, 0, 1); - set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id); - ret = cxgb4_ofld_send(csk->egress_dev, skb); - if (ret < 0) - kfree_skb(skb); -} - -/* TLS Key bitmap processing */ -int chtls_init_kmap(struct chtls_dev *cdev, struct cxgb4_lld_info *lldi) -{ - unsigned int num_key_ctx, bsize; - int ksize; - - num_key_ctx = (lldi->vr->key.size / TLS_KEY_CONTEXT_SZ); - bsize = BITS_TO_LONGS(num_key_ctx); - - cdev->kmap.size = num_key_ctx; - cdev->kmap.available = bsize; - ksize = sizeof(*cdev->kmap.addr) * bsize; - cdev->kmap.addr = kvzalloc(ksize, GFP_KERNEL); - if (!cdev->kmap.addr) - return -ENOMEM; - - cdev->kmap.start = lldi->vr->key.start; - spin_lock_init(&cdev->kmap.lock); - return 0; -} - -static int get_new_keyid(struct chtls_sock *csk, u32 optname) -{ - struct net_device *dev = csk->egress_dev; - struct chtls_dev *cdev = csk->cdev; - struct chtls_hws *hws; - struct adapter *adap; - int keyid; - - adap = netdev2adap(dev); - hws = &csk->tlshws; - - spin_lock_bh(&cdev->kmap.lock); - keyid = find_first_zero_bit(cdev->kmap.addr, cdev->kmap.size); - if (keyid < cdev->kmap.size) { - __set_bit(keyid, cdev->kmap.addr); - if (optname == TLS_RX) - hws->rxkey = keyid; - else - hws->txkey = keyid; - atomic_inc(&adap->chcr_stats.tls_key); - } else { - keyid = -1; - } - spin_unlock_bh(&cdev->kmap.lock); - return keyid; -} - -void free_tls_keyid(struct sock *sk) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct net_device *dev = csk->egress_dev; - struct chtls_dev *cdev = csk->cdev; - struct chtls_hws *hws; - struct adapter *adap; - - if (!cdev->kmap.addr) - return; - - adap = netdev2adap(dev); - hws = &csk->tlshws; - - spin_lock_bh(&cdev->kmap.lock); - if (hws->rxkey >= 0) { - __clear_bit(hws->rxkey, cdev->kmap.addr); - atomic_dec(&adap->chcr_stats.tls_key); - hws->rxkey = -1; - } - if (hws->txkey >= 0) { - __clear_bit(hws->txkey, cdev->kmap.addr); - atomic_dec(&adap->chcr_stats.tls_key); - hws->txkey = -1; - } - spin_unlock_bh(&cdev->kmap.lock); -} - -unsigned int keyid_to_addr(int start_addr, int keyid) -{ - return (start_addr + (keyid * TLS_KEY_CONTEXT_SZ)) >> 5; -} - -static void chtls_rxkey_ivauth(struct _key_ctx *kctx) -{ - kctx->iv_to_auth = cpu_to_be64(KEYCTX_TX_WR_IV_V(6ULL) | - KEYCTX_TX_WR_AAD_V(1ULL) | - KEYCTX_TX_WR_AADST_V(5ULL) | - KEYCTX_TX_WR_CIPHER_V(14ULL) | - KEYCTX_TX_WR_CIPHERST_V(0ULL) | - KEYCTX_TX_WR_AUTH_V(14ULL) | - KEYCTX_TX_WR_AUTHST_V(16ULL) | - KEYCTX_TX_WR_AUTHIN_V(16ULL)); -} - -static int chtls_key_info(struct chtls_sock *csk, - struct _key_ctx *kctx, - u32 keylen, u32 optname, - int cipher_type) -{ - unsigned char key[AES_MAX_KEY_SIZE]; - unsigned char *key_p, *salt; - unsigned char ghash_h[AEAD_H_SIZE]; - int ck_size, key_ctx_size, kctx_mackey_size, salt_size; - struct aes_enckey aes; - int ret; - - key_ctx_size = sizeof(struct _key_ctx) + - roundup(keylen, 16) + AEAD_H_SIZE; - - /* GCM mode of AES supports 128 and 256 bit encryption, so - * prepare key context base on GCM cipher type - */ - switch (cipher_type) { - case TLS_CIPHER_AES_GCM_128: { - struct tls12_crypto_info_aes_gcm_128 *gcm_ctx_128 = - (struct tls12_crypto_info_aes_gcm_128 *) - &csk->tlshws.crypto_info; - memcpy(key, gcm_ctx_128->key, keylen); - - key_p = gcm_ctx_128->key; - salt = gcm_ctx_128->salt; - ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128; - salt_size = TLS_CIPHER_AES_GCM_128_SALT_SIZE; - kctx_mackey_size = CHCR_KEYCTX_MAC_KEY_SIZE_128; - break; - } - case TLS_CIPHER_AES_GCM_256: { - struct tls12_crypto_info_aes_gcm_256 *gcm_ctx_256 = - (struct tls12_crypto_info_aes_gcm_256 *) - &csk->tlshws.crypto_info; - memcpy(key, gcm_ctx_256->key, keylen); - - key_p = gcm_ctx_256->key; - salt = gcm_ctx_256->salt; - ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256; - salt_size = TLS_CIPHER_AES_GCM_256_SALT_SIZE; - kctx_mackey_size = CHCR_KEYCTX_MAC_KEY_SIZE_256; - break; - } - default: - pr_err("GCM: Invalid key length %d\n", keylen); - return -EINVAL; - } - - /* Calculate the H = CIPH(K, 0 repeated 16 times). - * It will go in key context - */ - ret = aes_prepareenckey(&aes, key, keylen); - if (ret) - return ret; - - memset(ghash_h, 0, AEAD_H_SIZE); - aes_encrypt(&aes, ghash_h, ghash_h); - memzero_explicit(&aes, sizeof(aes)); - csk->tlshws.keylen = key_ctx_size; - - /* Copy the Key context */ - if (optname == TLS_RX) { - int key_ctx; - - key_ctx = ((key_ctx_size >> 4) << 3); - kctx->ctx_hdr = FILL_KEY_CRX_HDR(ck_size, - kctx_mackey_size, - 0, 0, key_ctx); - chtls_rxkey_ivauth(kctx); - } else { - kctx->ctx_hdr = FILL_KEY_CTX_HDR(ck_size, - kctx_mackey_size, - 0, 0, key_ctx_size >> 4); - } - - memcpy(kctx->salt, salt, salt_size); - memcpy(kctx->key, key_p, keylen); - memcpy(kctx->key + keylen, ghash_h, AEAD_H_SIZE); - /* erase key info from driver */ - memset(key_p, 0, keylen); - - return 0; -} - -static void chtls_set_scmd(struct chtls_sock *csk) -{ - struct chtls_hws *hws = &csk->tlshws; - - hws->scmd.seqno_numivs = - SCMD_SEQ_NO_CTRL_V(3) | - SCMD_PROTO_VERSION_V(0) | - SCMD_ENC_DEC_CTRL_V(0) | - SCMD_CIPH_AUTH_SEQ_CTRL_V(1) | - SCMD_CIPH_MODE_V(2) | - SCMD_AUTH_MODE_V(4) | - SCMD_HMAC_CTRL_V(0) | - SCMD_IV_SIZE_V(4) | - SCMD_NUM_IVS_V(1); - - hws->scmd.ivgen_hdrlen = - SCMD_IV_GEN_CTRL_V(1) | - SCMD_KEY_CTX_INLINE_V(0) | - SCMD_TLS_FRAG_ENABLE_V(1); -} - -int chtls_setkey(struct chtls_sock *csk, u32 keylen, - u32 optname, int cipher_type) -{ - struct tls_key_req *kwr; - struct chtls_dev *cdev; - struct _key_ctx *kctx; - int wrlen, klen, len; - struct sk_buff *skb; - struct sock *sk; - int keyid; - int kaddr; - int ret; - - cdev = csk->cdev; - sk = csk->sk; - - klen = roundup((keylen + AEAD_H_SIZE) + sizeof(*kctx), 32); - wrlen = roundup(sizeof(*kwr), 16); - len = klen + wrlen; - - /* Flush out-standing data before new key takes effect */ - if (optname == TLS_TX) { - lock_sock(sk); - if (skb_queue_len(&csk->txq)) - chtls_push_frames(csk, 0); - release_sock(sk); - } - - skb = alloc_skb(len, GFP_KERNEL); - if (!skb) - return -ENOMEM; - - keyid = get_new_keyid(csk, optname); - if (keyid < 0) { - ret = -ENOSPC; - goto out_nokey; - } - - kaddr = keyid_to_addr(cdev->kmap.start, keyid); - kwr = (struct tls_key_req *)__skb_put_zero(skb, len); - kwr->wr.op_to_compl = - cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) | FW_WR_COMPL_F | - FW_WR_ATOMIC_V(1U)); - kwr->wr.flowid_len16 = - cpu_to_be32(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16) | - FW_WR_FLOWID_V(csk->tid))); - kwr->wr.protocol = 0; - kwr->wr.mfs = htons(TLS_MFS); - kwr->wr.reneg_to_write_rx = optname; - - /* ulptx command */ - kwr->req.cmd = cpu_to_be32(ULPTX_CMD_V(ULP_TX_MEM_WRITE) | - T5_ULP_MEMIO_ORDER_V(1) | - T5_ULP_MEMIO_IMM_V(1)); - kwr->req.len16 = cpu_to_be32((csk->tid << 8) | - DIV_ROUND_UP(len - sizeof(kwr->wr), 16)); - kwr->req.dlen = cpu_to_be32(ULP_MEMIO_DATA_LEN_V(klen >> 5)); - kwr->req.lock_addr = cpu_to_be32(ULP_MEMIO_ADDR_V(kaddr)); - - /* sub command */ - kwr->sc_imm.cmd_more = cpu_to_be32(ULPTX_CMD_V(ULP_TX_SC_IMM)); - kwr->sc_imm.len = cpu_to_be32(klen); - - lock_sock(sk); - /* key info */ - kctx = (struct _key_ctx *)(kwr + 1); - ret = chtls_key_info(csk, kctx, keylen, optname, cipher_type); - if (ret) - goto out_notcb; - - if (unlikely(csk_flag(sk, CSK_ABORT_SHUTDOWN))) - goto out_notcb; - - set_wr_txq(skb, CPL_PRIORITY_DATA, csk->tlshws.txqid); - csk->wr_credits -= DIV_ROUND_UP(len, 16); - csk->wr_unacked += DIV_ROUND_UP(len, 16); - enqueue_wr(csk, skb); - cxgb4_ofld_send(csk->egress_dev, skb); - skb = NULL; - - chtls_set_scmd(csk); - /* Clear quiesce for Rx key */ - if (optname == TLS_RX) { - ret = chtls_set_tcb_keyid(sk, keyid); - if (ret) - goto out_notcb; - ret = chtls_set_tcb_field(sk, 0, - TCB_ULP_RAW_V(TCB_ULP_RAW_M), - TCB_ULP_RAW_V((TF_TLS_KEY_SIZE_V(1) | - TF_TLS_CONTROL_V(1) | - TF_TLS_ACTIVE_V(1) | - TF_TLS_ENABLE_V(1)))); - if (ret) - goto out_notcb; - ret = chtls_set_tcb_seqno(sk); - if (ret) - goto out_notcb; - ret = chtls_set_tcb_quiesce(sk, 0); - if (ret) - goto out_notcb; - csk->tlshws.rxkey = keyid; - } else { - csk->tlshws.tx_seq_no = 0; - csk->tlshws.txkey = keyid; - } - - release_sock(sk); - return ret; -out_notcb: - release_sock(sk); - free_tls_keyid(sk); -out_nokey: - kfree_skb(skb); - return ret; -} diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c deleted file mode 100644 index c8e99409a52a..000000000000 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ /dev/null @@ -1,1836 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2018 Chelsio Communications, Inc. - * - * Written by: Atul Gupta (atul.gupta@chelsio.com) - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "chtls.h" -#include "chtls_cm.h" - -static bool is_tls_tx(struct chtls_sock *csk) -{ - return csk->tlshws.txkey >= 0; -} - -static bool is_tls_rx(struct chtls_sock *csk) -{ - return csk->tlshws.rxkey >= 0; -} - -static int data_sgl_len(const struct sk_buff *skb) -{ - unsigned int cnt; - - cnt = skb_shinfo(skb)->nr_frags; - return sgl_len(cnt) * 8; -} - -static int nos_ivs(struct sock *sk, unsigned int size) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - - return DIV_ROUND_UP(size, csk->tlshws.mfs); -} - -static int set_ivs_imm(struct sock *sk, const struct sk_buff *skb) -{ - int ivs_size = nos_ivs(sk, skb->len) * CIPHER_BLOCK_SIZE; - int hlen = TLS_WR_CPL_LEN + data_sgl_len(skb); - - if ((hlen + KEY_ON_MEM_SZ + ivs_size) < - MAX_IMM_OFLD_TX_DATA_WR_LEN) { - ULP_SKB_CB(skb)->ulp.tls.iv = 1; - return 1; - } - ULP_SKB_CB(skb)->ulp.tls.iv = 0; - return 0; -} - -static int max_ivs_size(struct sock *sk, int size) -{ - return nos_ivs(sk, size) * CIPHER_BLOCK_SIZE; -} - -static int ivs_size(struct sock *sk, const struct sk_buff *skb) -{ - return set_ivs_imm(sk, skb) ? (nos_ivs(sk, skb->len) * - CIPHER_BLOCK_SIZE) : 0; -} - -static int flowc_wr_credits(int nparams, int *flowclenp) -{ - int flowclen16, flowclen; - - flowclen = offsetof(struct fw_flowc_wr, mnemval[nparams]); - flowclen16 = DIV_ROUND_UP(flowclen, 16); - flowclen = flowclen16 * 16; - - if (flowclenp) - *flowclenp = flowclen; - - return flowclen16; -} - -static struct sk_buff *create_flowc_wr_skb(struct sock *sk, - struct fw_flowc_wr *flowc, - int flowclen) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct sk_buff *skb; - - skb = alloc_skb(flowclen, GFP_ATOMIC); - if (!skb) - return NULL; - - __skb_put_data(skb, flowc, flowclen); - skb_set_queue_mapping(skb, (csk->txq_idx << 1) | CPL_PRIORITY_DATA); - - return skb; -} - -static int send_flowc_wr(struct sock *sk, struct fw_flowc_wr *flowc, - int flowclen) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - int flowclen16; - int ret; - - flowclen16 = flowclen / 16; - - if (csk_flag(sk, CSK_TX_DATA_SENT)) { - skb = create_flowc_wr_skb(sk, flowc, flowclen); - if (!skb) - return -ENOMEM; - - skb_entail(sk, skb, - ULPCB_FLAG_NO_HDR | ULPCB_FLAG_NO_APPEND); - return 0; - } - - ret = cxgb4_immdata_send(csk->egress_dev, - csk->txq_idx, - flowc, flowclen); - if (!ret) - return flowclen16; - skb = create_flowc_wr_skb(sk, flowc, flowclen); - if (!skb) - return -ENOMEM; - send_or_defer(sk, tp, skb, 0); - return flowclen16; -} - -static u8 tcp_state_to_flowc_state(u8 state) -{ - switch (state) { - case TCP_ESTABLISHED: - return FW_FLOWC_MNEM_TCPSTATE_ESTABLISHED; - case TCP_CLOSE_WAIT: - return FW_FLOWC_MNEM_TCPSTATE_CLOSEWAIT; - case TCP_FIN_WAIT1: - return FW_FLOWC_MNEM_TCPSTATE_FINWAIT1; - case TCP_CLOSING: - return FW_FLOWC_MNEM_TCPSTATE_CLOSING; - case TCP_LAST_ACK: - return FW_FLOWC_MNEM_TCPSTATE_LASTACK; - case TCP_FIN_WAIT2: - return FW_FLOWC_MNEM_TCPSTATE_FINWAIT2; - } - - return FW_FLOWC_MNEM_TCPSTATE_ESTABLISHED; -} - -int send_tx_flowc_wr(struct sock *sk, int compl, - u32 snd_nxt, u32 rcv_nxt) -{ - DEFINE_RAW_FLEX(struct fw_flowc_wr, flowc, mnemval, FW_FLOWC_MNEM_MAX); - int nparams, paramidx, flowclen16, flowclen; - struct chtls_sock *csk; - struct tcp_sock *tp; - - csk = rcu_dereference_sk_user_data(sk); - tp = tcp_sk(sk); - -#define FLOWC_PARAM(__m, __v) \ - do { \ - flowc->mnemval[paramidx].mnemonic = FW_FLOWC_MNEM_##__m; \ - flowc->mnemval[paramidx].val = cpu_to_be32(__v); \ - paramidx++; \ - } while (0) - - paramidx = 0; - - FLOWC_PARAM(PFNVFN, FW_PFVF_CMD_PFN_V(csk->cdev->lldi->pf)); - FLOWC_PARAM(CH, csk->tx_chan); - FLOWC_PARAM(PORT, csk->tx_chan); - FLOWC_PARAM(IQID, csk->rss_qid); - FLOWC_PARAM(SNDNXT, tp->snd_nxt); - FLOWC_PARAM(RCVNXT, tp->rcv_nxt); - FLOWC_PARAM(SNDBUF, csk->sndbuf); - FLOWC_PARAM(MSS, tp->mss_cache); - FLOWC_PARAM(TCPSTATE, tcp_state_to_flowc_state(sk->sk_state)); - - if (SND_WSCALE(tp)) - FLOWC_PARAM(RCV_SCALE, SND_WSCALE(tp)); - - if (csk->ulp_mode == ULP_MODE_TLS) - FLOWC_PARAM(ULD_MODE, ULP_MODE_TLS); - - if (csk->tlshws.fcplenmax) - FLOWC_PARAM(TXDATAPLEN_MAX, csk->tlshws.fcplenmax); - - nparams = paramidx; -#undef FLOWC_PARAM - - flowclen16 = flowc_wr_credits(nparams, &flowclen); - flowc->op_to_nparams = - cpu_to_be32(FW_WR_OP_V(FW_FLOWC_WR) | - FW_WR_COMPL_V(compl) | - FW_FLOWC_WR_NPARAMS_V(nparams)); - flowc->flowid_len16 = cpu_to_be32(FW_WR_LEN16_V(flowclen16) | - FW_WR_FLOWID_V(csk->tid)); - - return send_flowc_wr(sk, flowc, flowclen); -} - -/* Copy IVs to WR */ -static int tls_copy_ivs(struct sock *sk, struct sk_buff *skb) - -{ - struct chtls_sock *csk; - unsigned char *iv_loc; - struct chtls_hws *hws; - unsigned char *ivs; - u16 number_of_ivs; - struct page *page; - int err = 0; - - csk = rcu_dereference_sk_user_data(sk); - hws = &csk->tlshws; - number_of_ivs = nos_ivs(sk, skb->len); - - if (number_of_ivs > MAX_IVS_PAGE) { - pr_warn("MAX IVs in PAGE exceeded %d\n", number_of_ivs); - return -ENOMEM; - } - - /* generate the IVs */ - ivs = kmalloc_array(CIPHER_BLOCK_SIZE, number_of_ivs, GFP_ATOMIC); - if (!ivs) - return -ENOMEM; - get_random_bytes(ivs, number_of_ivs * CIPHER_BLOCK_SIZE); - - if (skb_ulp_tls_iv_imm(skb)) { - /* send the IVs as immediate data in the WR */ - iv_loc = (unsigned char *)__skb_push(skb, number_of_ivs * - CIPHER_BLOCK_SIZE); - if (iv_loc) - memcpy(iv_loc, ivs, number_of_ivs * CIPHER_BLOCK_SIZE); - - hws->ivsize = number_of_ivs * CIPHER_BLOCK_SIZE; - } else { - /* Send the IVs as sgls */ - /* Already accounted IV DSGL for credits */ - skb_shinfo(skb)->nr_frags--; - page = alloc_pages(sk->sk_allocation | __GFP_COMP, 0); - if (!page) { - pr_info("%s : Page allocation for IVs failed\n", - __func__); - err = -ENOMEM; - goto out; - } - memcpy(page_address(page), ivs, number_of_ivs * - CIPHER_BLOCK_SIZE); - skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, page, 0, - number_of_ivs * CIPHER_BLOCK_SIZE); - hws->ivsize = 0; - } -out: - kfree(ivs); - return err; -} - -/* Copy Key to WR */ -static void tls_copy_tx_key(struct sock *sk, struct sk_buff *skb) -{ - struct ulptx_sc_memrd *sc_memrd; - struct chtls_sock *csk; - struct chtls_dev *cdev; - struct ulptx_idata *sc; - struct chtls_hws *hws; - u32 immdlen; - int kaddr; - - csk = rcu_dereference_sk_user_data(sk); - hws = &csk->tlshws; - cdev = csk->cdev; - - immdlen = sizeof(*sc) + sizeof(*sc_memrd); - kaddr = keyid_to_addr(cdev->kmap.start, hws->txkey); - sc = (struct ulptx_idata *)__skb_push(skb, immdlen); - if (sc) { - sc->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP)); - sc->len = htonl(0); - sc_memrd = (struct ulptx_sc_memrd *)(sc + 1); - sc_memrd->cmd_to_len = - htonl(ULPTX_CMD_V(ULP_TX_SC_MEMRD) | - ULP_TX_SC_MORE_V(1) | - ULPTX_LEN16_V(hws->keylen >> 4)); - sc_memrd->addr = htonl(kaddr); - } -} - -static u64 tlstx_incr_seqnum(struct chtls_hws *hws) -{ - return hws->tx_seq_no++; -} - -static bool is_sg_request(const struct sk_buff *skb) -{ - return skb->peeked || - (skb->len > MAX_IMM_ULPTX_WR_LEN); -} - -/* - * Returns true if an sk_buff carries urgent data. - */ -static bool skb_urgent(struct sk_buff *skb) -{ - return ULP_SKB_CB(skb)->flags & ULPCB_FLAG_URG; -} - -/* TLS content type for CPL SFO */ -static unsigned char tls_content_type(unsigned char content_type) -{ - switch (content_type) { - case TLS_HDR_TYPE_CCS: - return CPL_TX_TLS_SFO_TYPE_CCS; - case TLS_HDR_TYPE_ALERT: - return CPL_TX_TLS_SFO_TYPE_ALERT; - case TLS_HDR_TYPE_HANDSHAKE: - return CPL_TX_TLS_SFO_TYPE_HANDSHAKE; - case TLS_HDR_TYPE_HEARTBEAT: - return CPL_TX_TLS_SFO_TYPE_HEARTBEAT; - } - return CPL_TX_TLS_SFO_TYPE_DATA; -} - -static void tls_tx_data_wr(struct sock *sk, struct sk_buff *skb, - int dlen, int tls_immd, u32 credits, - int expn, int pdus) -{ - struct fw_tlstx_data_wr *req_wr; - struct cpl_tx_tls_sfo *req_cpl; - unsigned int wr_ulp_mode_force; - struct tls_scmd *updated_scmd; - unsigned char data_type; - struct chtls_sock *csk; - struct net_device *dev; - struct chtls_hws *hws; - struct tls_scmd *scmd; - struct adapter *adap; - unsigned char *req; - int immd_len; - int iv_imm; - int len; - - csk = rcu_dereference_sk_user_data(sk); - iv_imm = skb_ulp_tls_iv_imm(skb); - dev = csk->egress_dev; - adap = netdev2adap(dev); - hws = &csk->tlshws; - scmd = &hws->scmd; - len = dlen + expn; - - dlen = (dlen < hws->mfs) ? dlen : hws->mfs; - atomic_inc(&adap->chcr_stats.tls_pdu_tx); - - updated_scmd = scmd; - updated_scmd->seqno_numivs &= 0xffffff80; - updated_scmd->seqno_numivs |= SCMD_NUM_IVS_V(pdus); - hws->scmd = *updated_scmd; - - req = (unsigned char *)__skb_push(skb, sizeof(struct cpl_tx_tls_sfo)); - req_cpl = (struct cpl_tx_tls_sfo *)req; - req = (unsigned char *)__skb_push(skb, (sizeof(struct - fw_tlstx_data_wr))); - - req_wr = (struct fw_tlstx_data_wr *)req; - immd_len = (tls_immd ? dlen : 0); - req_wr->op_to_immdlen = - htonl(FW_WR_OP_V(FW_TLSTX_DATA_WR) | - FW_TLSTX_DATA_WR_COMPL_V(1) | - FW_TLSTX_DATA_WR_IMMDLEN_V(immd_len)); - req_wr->flowid_len16 = htonl(FW_TLSTX_DATA_WR_FLOWID_V(csk->tid) | - FW_TLSTX_DATA_WR_LEN16_V(credits)); - wr_ulp_mode_force = TX_ULP_MODE_V(ULP_MODE_TLS); - - if (is_sg_request(skb)) - wr_ulp_mode_force |= FW_OFLD_TX_DATA_WR_ALIGNPLD_F | - ((tcp_sk(sk)->nonagle & TCP_NAGLE_OFF) ? 0 : - FW_OFLD_TX_DATA_WR_SHOVE_F); - - req_wr->lsodisable_to_flags = - htonl(TX_ULP_MODE_V(ULP_MODE_TLS) | - TX_URG_V(skb_urgent(skb)) | - T6_TX_FORCE_F | wr_ulp_mode_force | - TX_SHOVE_V((!csk_flag(sk, CSK_TX_MORE_DATA)) && - skb_queue_empty(&csk->txq))); - - req_wr->ctxloc_to_exp = - htonl(FW_TLSTX_DATA_WR_NUMIVS_V(pdus) | - FW_TLSTX_DATA_WR_EXP_V(expn) | - FW_TLSTX_DATA_WR_CTXLOC_V(CHTLS_KEY_CONTEXT_DDR) | - FW_TLSTX_DATA_WR_IVDSGL_V(!iv_imm) | - FW_TLSTX_DATA_WR_KEYSIZE_V(hws->keylen >> 4)); - - /* Fill in the length */ - req_wr->plen = htonl(len); - req_wr->mfs = htons(hws->mfs); - req_wr->adjustedplen_pkd = - htons(FW_TLSTX_DATA_WR_ADJUSTEDPLEN_V(hws->adjustlen)); - req_wr->expinplenmax_pkd = - htons(FW_TLSTX_DATA_WR_EXPINPLENMAX_V(hws->expansion)); - req_wr->pdusinplenmax_pkd = - FW_TLSTX_DATA_WR_PDUSINPLENMAX_V(hws->pdus); - req_wr->r10 = 0; - - data_type = tls_content_type(ULP_SKB_CB(skb)->ulp.tls.type); - req_cpl->op_to_seg_len = htonl(CPL_TX_TLS_SFO_OPCODE_V(CPL_TX_TLS_SFO) | - CPL_TX_TLS_SFO_DATA_TYPE_V(data_type) | - CPL_TX_TLS_SFO_CPL_LEN_V(2) | - CPL_TX_TLS_SFO_SEG_LEN_V(dlen)); - req_cpl->pld_len = htonl(len - expn); - - req_cpl->type_protover = htonl(CPL_TX_TLS_SFO_TYPE_V - ((data_type == CPL_TX_TLS_SFO_TYPE_HEARTBEAT) ? - TLS_HDR_TYPE_HEARTBEAT : 0) | - CPL_TX_TLS_SFO_PROTOVER_V(0)); - - /* create the s-command */ - req_cpl->r1_lo = 0; - req_cpl->seqno_numivs = cpu_to_be32(hws->scmd.seqno_numivs); - req_cpl->ivgen_hdrlen = cpu_to_be32(hws->scmd.ivgen_hdrlen); - req_cpl->scmd1 = cpu_to_be64(tlstx_incr_seqnum(hws)); -} - -/* - * Calculate the TLS data expansion size - */ -static int chtls_expansion_size(struct sock *sk, int data_len, - int fullpdu, - unsigned short *pducnt) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct chtls_hws *hws = &csk->tlshws; - struct tls_scmd *scmd = &hws->scmd; - int fragsize = hws->mfs; - int expnsize = 0; - int fragleft; - int fragcnt; - int expppdu; - - if (SCMD_CIPH_MODE_G(scmd->seqno_numivs) == - SCMD_CIPH_MODE_AES_GCM) { - expppdu = GCM_TAG_SIZE + AEAD_EXPLICIT_DATA_SIZE + - TLS_HEADER_LENGTH; - - if (fullpdu) { - *pducnt = data_len / (expppdu + fragsize); - if (*pducnt > 32) - *pducnt = 32; - else if (!*pducnt) - *pducnt = 1; - expnsize = (*pducnt) * expppdu; - return expnsize; - } - fragcnt = (data_len / fragsize); - expnsize = fragcnt * expppdu; - fragleft = data_len % fragsize; - if (fragleft > 0) - expnsize += expppdu; - } - return expnsize; -} - -/* WR with IV, KEY and CPL SFO added */ -static void make_tlstx_data_wr(struct sock *sk, struct sk_buff *skb, - int tls_tx_imm, int tls_len, u32 credits) -{ - unsigned short pdus_per_ulp = 0; - struct chtls_sock *csk; - struct chtls_hws *hws; - int expn_sz; - int pdus; - - csk = rcu_dereference_sk_user_data(sk); - hws = &csk->tlshws; - pdus = DIV_ROUND_UP(tls_len, hws->mfs); - expn_sz = chtls_expansion_size(sk, tls_len, 0, NULL); - if (!hws->compute) { - hws->expansion = chtls_expansion_size(sk, - hws->fcplenmax, - 1, &pdus_per_ulp); - hws->pdus = pdus_per_ulp; - hws->adjustlen = hws->pdus * - ((hws->expansion / hws->pdus) + hws->mfs); - hws->compute = 1; - } - if (tls_copy_ivs(sk, skb)) - return; - tls_copy_tx_key(sk, skb); - tls_tx_data_wr(sk, skb, tls_len, tls_tx_imm, credits, expn_sz, pdus); - hws->tx_seq_no += (pdus - 1); -} - -static void make_tx_data_wr(struct sock *sk, struct sk_buff *skb, - unsigned int immdlen, int len, - u32 credits, u32 compl) -{ - struct fw_ofld_tx_data_wr *req; - unsigned int wr_ulp_mode_force; - struct chtls_sock *csk; - unsigned int opcode; - - csk = rcu_dereference_sk_user_data(sk); - opcode = FW_OFLD_TX_DATA_WR; - - req = (struct fw_ofld_tx_data_wr *)__skb_push(skb, sizeof(*req)); - req->op_to_immdlen = htonl(WR_OP_V(opcode) | - FW_WR_COMPL_V(compl) | - FW_WR_IMMDLEN_V(immdlen)); - req->flowid_len16 = htonl(FW_WR_FLOWID_V(csk->tid) | - FW_WR_LEN16_V(credits)); - - wr_ulp_mode_force = TX_ULP_MODE_V(csk->ulp_mode); - if (is_sg_request(skb)) - wr_ulp_mode_force |= FW_OFLD_TX_DATA_WR_ALIGNPLD_F | - ((tcp_sk(sk)->nonagle & TCP_NAGLE_OFF) ? 0 : - FW_OFLD_TX_DATA_WR_SHOVE_F); - - req->tunnel_to_proxy = htonl(wr_ulp_mode_force | - TX_URG_V(skb_urgent(skb)) | - TX_SHOVE_V((!csk_flag(sk, CSK_TX_MORE_DATA)) && - skb_queue_empty(&csk->txq))); - req->plen = htonl(len); -} - -static int chtls_wr_size(struct chtls_sock *csk, const struct sk_buff *skb, - bool size) -{ - int wr_size; - - wr_size = TLS_WR_CPL_LEN; - wr_size += KEY_ON_MEM_SZ; - wr_size += ivs_size(csk->sk, skb); - - if (size) - return wr_size; - - /* frags counted for IV dsgl */ - if (!skb_ulp_tls_iv_imm(skb)) - skb_shinfo(skb)->nr_frags++; - - return wr_size; -} - -static bool is_ofld_imm(struct chtls_sock *csk, const struct sk_buff *skb) -{ - int length = skb->len; - - if (skb->peeked || skb->len > MAX_IMM_ULPTX_WR_LEN) - return false; - - if (likely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NEED_HDR)) { - /* Check TLS header len for Immediate */ - if (csk->ulp_mode == ULP_MODE_TLS && - skb_ulp_tls_inline(skb)) - length += chtls_wr_size(csk, skb, true); - else - length += sizeof(struct fw_ofld_tx_data_wr); - - return length <= MAX_IMM_OFLD_TX_DATA_WR_LEN; - } - return true; -} - -static unsigned int calc_tx_flits(const struct sk_buff *skb, - unsigned int immdlen) -{ - unsigned int flits, cnt; - - flits = immdlen / 8; /* headers */ - cnt = skb_shinfo(skb)->nr_frags; - if (skb_tail_pointer(skb) != skb_transport_header(skb)) - cnt++; - return flits + sgl_len(cnt); -} - -static void arp_failure_discard(void *handle, struct sk_buff *skb) -{ - kfree_skb(skb); -} - -int chtls_push_frames(struct chtls_sock *csk, int comp) -{ - struct chtls_hws *hws = &csk->tlshws; - struct tcp_sock *tp; - struct sk_buff *skb; - int total_size = 0; - struct sock *sk; - int wr_size; - - wr_size = sizeof(struct fw_ofld_tx_data_wr); - sk = csk->sk; - tp = tcp_sk(sk); - - if (unlikely(sk_in_state(sk, TCPF_SYN_SENT | TCPF_CLOSE))) - return 0; - - if (unlikely(csk_flag(sk, CSK_ABORT_SHUTDOWN))) - return 0; - - while (csk->wr_credits && (skb = skb_peek(&csk->txq)) && - (!(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_HOLD) || - skb_queue_len(&csk->txq) > 1)) { - unsigned int credit_len = skb->len; - unsigned int credits_needed; - unsigned int completion = 0; - int tls_len = skb->len;/* TLS data len before IV/key */ - unsigned int immdlen; - int len = skb->len; /* length [ulp bytes] inserted by hw */ - int flowclen16 = 0; - int tls_tx_imm = 0; - - immdlen = skb->len; - if (!is_ofld_imm(csk, skb)) { - immdlen = skb_transport_offset(skb); - if (skb_ulp_tls_inline(skb)) - wr_size = chtls_wr_size(csk, skb, false); - credit_len = 8 * calc_tx_flits(skb, immdlen); - } else { - if (skb_ulp_tls_inline(skb)) { - wr_size = chtls_wr_size(csk, skb, false); - tls_tx_imm = 1; - } - } - if (likely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NEED_HDR)) - credit_len += wr_size; - credits_needed = DIV_ROUND_UP(credit_len, 16); - if (!csk_flag_nochk(csk, CSK_TX_DATA_SENT)) { - flowclen16 = send_tx_flowc_wr(sk, 1, tp->snd_nxt, - tp->rcv_nxt); - if (flowclen16 <= 0) - break; - csk->wr_credits -= flowclen16; - csk->wr_unacked += flowclen16; - csk->wr_nondata += flowclen16; - csk_set_flag(csk, CSK_TX_DATA_SENT); - } - - if (csk->wr_credits < credits_needed) { - if (skb_ulp_tls_inline(skb) && - !skb_ulp_tls_iv_imm(skb)) - skb_shinfo(skb)->nr_frags--; - break; - } - - __skb_unlink(skb, &csk->txq); - skb_set_queue_mapping(skb, (csk->txq_idx << 1) | - CPL_PRIORITY_DATA); - if (hws->ofld) - hws->txqid = (skb->queue_mapping >> 1); - skb->csum = (__force __wsum)(credits_needed + csk->wr_nondata); - csk->wr_credits -= credits_needed; - csk->wr_unacked += credits_needed; - csk->wr_nondata = 0; - enqueue_wr(csk, skb); - - if (likely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NEED_HDR)) { - if ((comp && csk->wr_unacked == credits_needed) || - (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_COMPL) || - csk->wr_unacked >= csk->wr_max_credits / 2) { - completion = 1; - csk->wr_unacked = 0; - } - if (skb_ulp_tls_inline(skb)) - make_tlstx_data_wr(sk, skb, tls_tx_imm, - tls_len, credits_needed); - else - make_tx_data_wr(sk, skb, immdlen, len, - credits_needed, completion); - tp->snd_nxt += len; - tp->lsndtime = tcp_jiffies32; - if (completion) - ULP_SKB_CB(skb)->flags &= ~ULPCB_FLAG_NEED_HDR; - } else { - struct cpl_close_con_req *req = cplhdr(skb); - unsigned int cmd = CPL_OPCODE_G(ntohl - (OPCODE_TID(req))); - - if (cmd == CPL_CLOSE_CON_REQ) - csk_set_flag(csk, - CSK_CLOSE_CON_REQUESTED); - - if ((ULP_SKB_CB(skb)->flags & ULPCB_FLAG_COMPL) && - (csk->wr_unacked >= csk->wr_max_credits / 2)) { - req->wr.wr_hi |= htonl(FW_WR_COMPL_F); - csk->wr_unacked = 0; - } - } - total_size += skb->truesize; - if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_BARRIER) - csk_set_flag(csk, CSK_TX_WAIT_IDLE); - t4_set_arp_err_handler(skb, NULL, arp_failure_discard); - cxgb4_l2t_send(csk->egress_dev, skb, csk->l2t_entry); - } - sk->sk_wmem_queued -= total_size; - return total_size; -} - -static void mark_urg(struct tcp_sock *tp, int flags, - struct sk_buff *skb) -{ - if (unlikely(flags & MSG_OOB)) { - tp->snd_up = tp->write_seq; - ULP_SKB_CB(skb)->flags = ULPCB_FLAG_URG | - ULPCB_FLAG_BARRIER | - ULPCB_FLAG_NO_APPEND | - ULPCB_FLAG_NEED_HDR; - } -} - -/* - * Returns true if a connection should send more data to TCP engine - */ -static bool should_push(struct sock *sk) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct chtls_dev *cdev = csk->cdev; - struct tcp_sock *tp = tcp_sk(sk); - - /* - * If we've released our offload resources there's nothing to do ... - */ - if (!cdev) - return false; - - /* - * If there aren't any work requests in flight, or there isn't enough - * data in flight, or Nagle is off then send the current TX_DATA - * otherwise hold it and wait to accumulate more data. - */ - return csk->wr_credits == csk->wr_max_credits || - (tp->nonagle & TCP_NAGLE_OFF); -} - -/* - * Returns true if a TCP socket is corked. - */ -static bool corked(const struct tcp_sock *tp, int flags) -{ - return (flags & MSG_MORE) || (tp->nonagle & TCP_NAGLE_CORK); -} - -/* - * Returns true if a send should try to push new data. - */ -static bool send_should_push(struct sock *sk, int flags) -{ - return should_push(sk) && !corked(tcp_sk(sk), flags); -} - -void chtls_tcp_push(struct sock *sk, int flags) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - int qlen = skb_queue_len(&csk->txq); - - if (likely(qlen)) { - struct sk_buff *skb = skb_peek_tail(&csk->txq); - struct tcp_sock *tp = tcp_sk(sk); - - mark_urg(tp, flags, skb); - - if (!(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) && - corked(tp, flags)) { - ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_HOLD; - return; - } - - ULP_SKB_CB(skb)->flags &= ~ULPCB_FLAG_HOLD; - if (qlen == 1 && - ((ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) || - should_push(sk))) - chtls_push_frames(csk, 1); - } -} - -/* - * Calculate the size for a new send sk_buff. It's maximum size so we can - * pack lots of data into it, unless we plan to send it immediately, in which - * case we size it more tightly. - * - * Note: we don't bother compensating for MSS < PAGE_SIZE because it doesn't - * arise in normal cases and when it does we are just wasting memory. - */ -static int select_size(struct sock *sk, int io_len, int flags, int len) -{ - const int pgbreak = SKB_MAX_HEAD(len); - - /* - * If the data wouldn't fit in the main body anyway, put only the - * header in the main body so it can use immediate data and place all - * the payload in page fragments. - */ - if (io_len > pgbreak) - return 0; - - /* - * If we will be accumulating payload get a large main body. - */ - if (!send_should_push(sk, flags)) - return pgbreak; - - return io_len; -} - -void skb_entail(struct sock *sk, struct sk_buff *skb, int flags) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct tcp_sock *tp = tcp_sk(sk); - - ULP_SKB_CB(skb)->seq = tp->write_seq; - ULP_SKB_CB(skb)->flags = flags; - __skb_queue_tail(&csk->txq, skb); - sk->sk_wmem_queued += skb->truesize; - - if (TCP_PAGE(sk) && TCP_OFF(sk)) { - put_page(TCP_PAGE(sk)); - TCP_PAGE(sk) = NULL; - TCP_OFF(sk) = 0; - } -} - -static struct sk_buff *get_tx_skb(struct sock *sk, int size) -{ - struct sk_buff *skb; - - skb = alloc_skb(size + TX_HEADER_LEN, sk->sk_allocation); - if (likely(skb)) { - skb_reserve(skb, TX_HEADER_LEN); - skb_entail(sk, skb, ULPCB_FLAG_NEED_HDR); - skb_reset_transport_header(skb); - } - return skb; -} - -static struct sk_buff *get_record_skb(struct sock *sk, int size, bool zcopy) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct sk_buff *skb; - - skb = alloc_skb(((zcopy ? 0 : size) + TX_TLSHDR_LEN + - KEY_ON_MEM_SZ + max_ivs_size(sk, size)), - sk->sk_allocation); - if (likely(skb)) { - skb_reserve(skb, (TX_TLSHDR_LEN + - KEY_ON_MEM_SZ + max_ivs_size(sk, size))); - skb_entail(sk, skb, ULPCB_FLAG_NEED_HDR); - skb_reset_transport_header(skb); - ULP_SKB_CB(skb)->ulp.tls.ofld = 1; - ULP_SKB_CB(skb)->ulp.tls.type = csk->tlshws.type; - } - return skb; -} - -static void tx_skb_finalize(struct sk_buff *skb) -{ - struct ulp_skb_cb *cb = ULP_SKB_CB(skb); - - if (!(cb->flags & ULPCB_FLAG_NO_HDR)) - cb->flags = ULPCB_FLAG_NEED_HDR; - cb->flags |= ULPCB_FLAG_NO_APPEND; -} - -static void push_frames_if_head(struct sock *sk) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - - if (skb_queue_len(&csk->txq) == 1) - chtls_push_frames(csk, 1); -} - -static int chtls_skb_copy_to_page_nocache(struct sock *sk, - struct iov_iter *from, - struct sk_buff *skb, - struct page *page, - int off, int copy) -{ - int err; - - err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + - off, copy, skb->len); - if (err) - return err; - - skb->len += copy; - skb->data_len += copy; - skb->truesize += copy; - sk->sk_wmem_queued += copy; - return 0; -} - -static bool csk_mem_free(struct chtls_dev *cdev, struct sock *sk) -{ - return (cdev->max_host_sndbuf - sk->sk_wmem_queued > 0); -} - -static int csk_wait_memory(struct chtls_dev *cdev, - struct sock *sk, long *timeo_p) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int ret, err = 0; - long current_timeo; - long vm_wait = 0; - bool noblock; - - current_timeo = *timeo_p; - noblock = (*timeo_p ? false : true); - if (csk_mem_free(cdev, sk)) { - current_timeo = get_random_u32_below(HZ / 5) + 2; - vm_wait = get_random_u32_below(HZ / 5) + 2; - } - - add_wait_queue(sk_sleep(sk), &wait); - while (1) { - sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); - - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) - goto do_error; - if (!*timeo_p) { - if (noblock) - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - goto do_nonblock; - } - if (signal_pending(current)) - goto do_interrupted; - sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (csk_mem_free(cdev, sk) && !vm_wait) - break; - - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - sk->sk_write_pending++; - ret = sk_wait_event(sk, ¤t_timeo, sk->sk_err || - (sk->sk_shutdown & SEND_SHUTDOWN) || - (csk_mem_free(cdev, sk) && !vm_wait), - &wait); - sk->sk_write_pending--; - if (ret < 0) - goto do_error; - - if (vm_wait) { - vm_wait -= current_timeo; - current_timeo = *timeo_p; - if (current_timeo != MAX_SCHEDULE_TIMEOUT) { - current_timeo -= vm_wait; - if (current_timeo < 0) - current_timeo = 0; - } - vm_wait = 0; - } - *timeo_p = current_timeo; - } -do_rm_wq: - remove_wait_queue(sk_sleep(sk), &wait); - return err; -do_error: - err = -EPIPE; - goto do_rm_wq; -do_nonblock: - err = -EAGAIN; - goto do_rm_wq; -do_interrupted: - err = sock_intr_errno(*timeo_p); - goto do_rm_wq; -} - -static int chtls_proccess_cmsg(struct sock *sk, struct msghdr *msg, - unsigned char *record_type) -{ - struct cmsghdr *cmsg; - int rc = -EINVAL; - - for_each_cmsghdr(cmsg, msg) { - if (!CMSG_OK(msg, cmsg)) - return -EINVAL; - if (cmsg->cmsg_level != SOL_TLS) - continue; - - switch (cmsg->cmsg_type) { - case TLS_SET_RECORD_TYPE: - if (cmsg->cmsg_len < CMSG_LEN(sizeof(*record_type))) - return -EINVAL; - - if (msg->msg_flags & MSG_MORE) - return -EINVAL; - - *record_type = *(unsigned char *)CMSG_DATA(cmsg); - rc = 0; - break; - default: - return -EINVAL; - } - } - - return rc; -} - -int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct chtls_dev *cdev = csk->cdev; - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - int mss, flags, err; - int recordsz = 0; - int copied = 0; - long timeo; - - lock_sock(sk); - flags = msg->msg_flags; - timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - - if (!sk_in_state(sk, TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { - err = sk_stream_wait_connect(sk, &timeo); - if (err) - goto out_err; - } - - sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - err = -EPIPE; - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) - goto out_err; - - mss = csk->mss; - csk_set_flag(csk, CSK_TX_MORE_DATA); - - while (msg_data_left(msg)) { - int copy = 0; - - skb = skb_peek_tail(&csk->txq); - if (skb) { - copy = mss - skb->len; - skb->ip_summed = CHECKSUM_UNNECESSARY; - } - if (!csk_mem_free(cdev, sk)) - goto wait_for_sndbuf; - - if (is_tls_tx(csk) && !csk->tlshws.txleft) { - unsigned char record_type = TLS_RECORD_TYPE_DATA; - - if (unlikely(msg->msg_controllen)) { - err = chtls_proccess_cmsg(sk, msg, - &record_type); - if (err) - goto out_err; - - /* Avoid appending tls handshake, alert to tls data */ - if (skb) - tx_skb_finalize(skb); - } - - recordsz = size; - csk->tlshws.txleft = recordsz; - csk->tlshws.type = record_type; - } - - if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) || - copy <= 0) { -new_buf: - if (skb) { - tx_skb_finalize(skb); - push_frames_if_head(sk); - } - - if (is_tls_tx(csk)) { - skb = get_record_skb(sk, - select_size(sk, - recordsz, - flags, - TX_TLSHDR_LEN), - false); - } else { - skb = get_tx_skb(sk, - select_size(sk, size, flags, - TX_HEADER_LEN)); - } - if (unlikely(!skb)) - goto wait_for_memory; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - copy = mss; - } - if (copy > size) - copy = size; - - if (msg->msg_flags & MSG_SPLICE_PAGES) { - err = skb_splice_from_iter(skb, &msg->msg_iter, copy); - if (err < 0) { - if (err == -EMSGSIZE) - goto new_buf; - goto do_fault; - } - copy = err; - sk_wmem_queued_add(sk, copy); - } else if (skb_tailroom(skb) > 0) { - copy = min(copy, skb_tailroom(skb)); - if (is_tls_tx(csk)) - copy = min_t(int, copy, csk->tlshws.txleft); - err = skb_add_data_nocache(sk, skb, - &msg->msg_iter, copy); - if (err) - goto do_fault; - } else { - int i = skb_shinfo(skb)->nr_frags; - struct page *page = TCP_PAGE(sk); - int pg_size = PAGE_SIZE; - int off = TCP_OFF(sk); - bool merge; - - if (page) - pg_size = page_size(page); - if (off < pg_size && - skb_can_coalesce(skb, i, page, off)) { - merge = true; - goto copy; - } - merge = false; - if (i == (is_tls_tx(csk) ? (MAX_SKB_FRAGS - 1) : - MAX_SKB_FRAGS)) - goto new_buf; - - if (page && off == pg_size) { - put_page(page); - TCP_PAGE(sk) = page = NULL; - pg_size = PAGE_SIZE; - } - - if (!page) { - gfp_t gfp = sk->sk_allocation; - int order = cdev->send_page_order; - - if (order) { - page = alloc_pages(gfp | __GFP_COMP | - __GFP_NOWARN | - __GFP_NORETRY, - order); - if (page) - pg_size <<= order; - } - if (!page) { - page = alloc_page(gfp); - pg_size = PAGE_SIZE; - } - if (!page) - goto wait_for_memory; - off = 0; - } -copy: - if (copy > pg_size - off) - copy = pg_size - off; - if (is_tls_tx(csk)) - copy = min_t(int, copy, csk->tlshws.txleft); - - err = chtls_skb_copy_to_page_nocache(sk, &msg->msg_iter, - skb, page, - off, copy); - if (unlikely(err)) { - if (!TCP_PAGE(sk)) { - TCP_PAGE(sk) = page; - TCP_OFF(sk) = 0; - } - goto do_fault; - } - /* Update the skb. */ - if (merge) { - skb_frag_size_add( - &skb_shinfo(skb)->frags[i - 1], - copy); - } else { - skb_fill_page_desc(skb, i, page, off, copy); - if (off + copy < pg_size) { - /* space left keep page */ - get_page(page); - TCP_PAGE(sk) = page; - } else { - TCP_PAGE(sk) = NULL; - } - } - TCP_OFF(sk) = off + copy; - } - if (unlikely(skb->len == mss)) - tx_skb_finalize(skb); - tp->write_seq += copy; - copied += copy; - size -= copy; - - if (is_tls_tx(csk)) - csk->tlshws.txleft -= copy; - - if (corked(tp, flags) && - (sk_stream_wspace(sk) < sk_stream_min_wspace(sk))) - ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_NO_APPEND; - - if (size == 0) - goto out; - - if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) - push_frames_if_head(sk); - continue; -wait_for_sndbuf: - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -wait_for_memory: - err = csk_wait_memory(cdev, sk, &timeo); - if (err) - goto do_error; - } -out: - csk_reset_flag(csk, CSK_TX_MORE_DATA); - if (copied) - chtls_tcp_push(sk, flags); -done: - release_sock(sk); - return copied; -do_fault: - if (!skb->len) { - __skb_unlink(skb, &csk->txq); - sk->sk_wmem_queued -= skb->truesize; - __kfree_skb(skb); - } -do_error: - if (copied) - goto out; -out_err: - if (csk_conn_inline(csk)) - csk_reset_flag(csk, CSK_TX_MORE_DATA); - copied = sk_stream_error(sk, flags, err); - goto done; -} - -void chtls_splice_eof(struct socket *sock) -{ - struct sock *sk = sock->sk; - - lock_sock(sk); - chtls_tcp_push(sk, 0); - release_sock(sk); -} - -static void chtls_select_window(struct sock *sk) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct tcp_sock *tp = tcp_sk(sk); - unsigned int wnd = tp->rcv_wnd; - - wnd = max_t(unsigned int, wnd, tcp_full_space(sk)); - wnd = max_t(unsigned int, MIN_RCV_WND, wnd); - - if (wnd > MAX_RCV_WND) - wnd = MAX_RCV_WND; - -/* - * Check if we need to grow the receive window in response to an increase in - * the socket's receive buffer size. Some applications increase the buffer - * size dynamically and rely on the window to grow accordingly. - */ - - if (wnd > tp->rcv_wnd) { - tp->rcv_wup -= wnd - tp->rcv_wnd; - tp->rcv_wnd = wnd; - /* Mark the receive window as updated */ - csk_reset_flag(csk, CSK_UPDATE_RCV_WND); - } -} - -/* - * Send RX credits through an RX_DATA_ACK CPL message. We are permitted - * to return without sending the message in case we cannot allocate - * an sk_buff. Returns the number of credits sent. - */ -static u32 send_rx_credits(struct chtls_sock *csk, u32 credits) -{ - struct cpl_rx_data_ack *req; - struct sk_buff *skb; - - skb = alloc_skb(sizeof(*req), GFP_ATOMIC); - if (!skb) - return 0; - __skb_put(skb, sizeof(*req)); - req = (struct cpl_rx_data_ack *)skb->head; - - set_wr_txq(skb, CPL_PRIORITY_ACK, csk->port_id); - INIT_TP_WR(req, csk->tid); - OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK, - csk->tid)); - req->credit_dack = cpu_to_be32(RX_CREDITS_V(credits) | - RX_FORCE_ACK_F); - cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb); - return credits; -} - -#define CREDIT_RETURN_STATE (TCPF_ESTABLISHED | \ - TCPF_FIN_WAIT1 | \ - TCPF_FIN_WAIT2) - -/* - * Called after some received data has been read. It returns RX credits - * to the HW for the amount of data processed. - */ -static void chtls_cleanup_rbuf(struct sock *sk, int copied) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct tcp_sock *tp; - int must_send; - u32 credits; - u32 thres; - - thres = 15 * 1024; - - if (!sk_in_state(sk, CREDIT_RETURN_STATE)) - return; - - chtls_select_window(sk); - tp = tcp_sk(sk); - credits = tp->copied_seq - tp->rcv_wup; - if (unlikely(!credits)) - return; - -/* - * For coalescing to work effectively ensure the receive window has - * at least 16KB left. - */ - must_send = credits + 16384 >= tp->rcv_wnd; - - if (must_send || credits >= thres) - tp->rcv_wup += send_rx_credits(csk, credits); -} - -static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int flags) -{ - struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); - struct chtls_hws *hws = &csk->tlshws; - struct net_device *dev = csk->egress_dev; - struct adapter *adap = netdev2adap(dev); - struct tcp_sock *tp = tcp_sk(sk); - unsigned long avail; - int buffers_freed; - int copied = 0; - int target; - long timeo; - int ret; - - buffers_freed = 0; - - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - - if (unlikely(csk_flag(sk, CSK_UPDATE_RCV_WND))) - chtls_cleanup_rbuf(sk, copied); - - do { - struct sk_buff *skb; - u32 offset = 0; - - if (unlikely(tp->urg_data && - tp->urg_seq == tp->copied_seq)) { - if (copied) - break; - if (signal_pending(current)) { - copied = timeo ? sock_intr_errno(timeo) : - -EAGAIN; - break; - } - } - skb = skb_peek(&sk->sk_receive_queue); - if (skb) - goto found_ok_skb; - if (csk->wr_credits && - skb_queue_len(&csk->txq) && - chtls_push_frames(csk, csk->wr_credits == - csk->wr_max_credits)) - sk->sk_write_space(sk); - - if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) - break; - - if (copied) { - if (sk->sk_err || sk->sk_state == TCP_CLOSE || - (sk->sk_shutdown & RCV_SHUTDOWN) || - signal_pending(current)) - break; - - if (!timeo) - break; - } else { - if (sock_flag(sk, SOCK_DONE)) - break; - if (sk->sk_err) { - copied = sock_error(sk); - break; - } - if (sk->sk_shutdown & RCV_SHUTDOWN) - break; - if (sk->sk_state == TCP_CLOSE) { - copied = -ENOTCONN; - break; - } - if (!timeo) { - copied = -EAGAIN; - break; - } - if (signal_pending(current)) { - copied = sock_intr_errno(timeo); - break; - } - } - if (READ_ONCE(sk->sk_backlog.tail)) { - release_sock(sk); - lock_sock(sk); - chtls_cleanup_rbuf(sk, copied); - continue; - } - - if (copied >= target) - break; - chtls_cleanup_rbuf(sk, copied); - ret = sk_wait_data(sk, &timeo, NULL); - if (ret < 0) { - copied = copied ? : ret; - goto unlock; - } - continue; -found_ok_skb: - if (!skb->len) { - skb_dstref_steal(skb); - __skb_unlink(skb, &sk->sk_receive_queue); - kfree_skb(skb); - - if (!copied && !timeo) { - copied = -EAGAIN; - break; - } - - if (copied < target) { - release_sock(sk); - lock_sock(sk); - continue; - } - break; - } - offset = hws->copied_seq; - avail = skb->len - offset; - if (len < avail) - avail = len; - - if (unlikely(tp->urg_data)) { - u32 urg_offset = tp->urg_seq - tp->copied_seq; - - if (urg_offset < avail) { - if (urg_offset) { - avail = urg_offset; - } else if (!sock_flag(sk, SOCK_URGINLINE)) { - /* First byte is urgent, skip */ - tp->copied_seq++; - offset++; - avail--; - if (!avail) - goto skip_copy; - } - } - } - /* Set record type if not already done. For a non-data record, - * do not proceed if record type could not be copied. - */ - if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) { - struct tls_hdr *thdr = (struct tls_hdr *)skb->data; - int cerr = 0; - - cerr = put_cmsg(msg, SOL_TLS, TLS_GET_RECORD_TYPE, - sizeof(thdr->type), &thdr->type); - - if (cerr && thdr->type != TLS_RECORD_TYPE_DATA) { - copied = -EIO; - break; - } - /* don't send tls header, skip copy */ - goto skip_copy; - } - - if (skb_copy_datagram_msg(skb, offset, msg, avail)) { - if (!copied) { - copied = -EFAULT; - break; - } - } - - copied += avail; - len -= avail; - hws->copied_seq += avail; -skip_copy: - if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) - tp->urg_data = 0; - - if ((avail + offset) >= skb->len) { - struct sk_buff *next_skb; - if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) { - tp->copied_seq += skb->len; - hws->rcvpld = skb->hdr_len; - } else { - atomic_inc(&adap->chcr_stats.tls_pdu_rx); - tp->copied_seq += hws->rcvpld; - } - chtls_free_skb(sk, skb); - buffers_freed++; - hws->copied_seq = 0; - next_skb = skb_peek(&sk->sk_receive_queue); - if (copied >= target && !next_skb) - break; - if (ULP_SKB_CB(next_skb)->flags & ULPCB_FLAG_TLS_HDR) - break; - } - } while (len > 0); - - if (buffers_freed) - chtls_cleanup_rbuf(sk, copied); - -unlock: - release_sock(sk); - return copied; -} - -/* - * Peek at data in a socket's receive buffer. - */ -static int peekmsg(struct sock *sk, struct msghdr *msg, - size_t len, int flags) -{ - struct tcp_sock *tp = tcp_sk(sk); - u32 peek_seq, offset; - struct sk_buff *skb; - int copied = 0; - size_t avail; /* amount of available data in current skb */ - long timeo; - int ret; - - lock_sock(sk); - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - peek_seq = tp->copied_seq; - - do { - if (unlikely(tp->urg_data && tp->urg_seq == peek_seq)) { - if (copied) - break; - if (signal_pending(current)) { - copied = timeo ? sock_intr_errno(timeo) : - -EAGAIN; - break; - } - } - - skb_queue_walk(&sk->sk_receive_queue, skb) { - offset = peek_seq - ULP_SKB_CB(skb)->seq; - if (offset < skb->len) - goto found_ok_skb; - } - - /* empty receive queue */ - if (copied) - break; - if (sock_flag(sk, SOCK_DONE)) - break; - if (sk->sk_err) { - copied = sock_error(sk); - break; - } - if (sk->sk_shutdown & RCV_SHUTDOWN) - break; - if (sk->sk_state == TCP_CLOSE) { - copied = -ENOTCONN; - break; - } - if (!timeo) { - copied = -EAGAIN; - break; - } - if (signal_pending(current)) { - copied = sock_intr_errno(timeo); - break; - } - - if (READ_ONCE(sk->sk_backlog.tail)) { - /* Do not sleep, just process backlog. */ - release_sock(sk); - lock_sock(sk); - } else { - ret = sk_wait_data(sk, &timeo, NULL); - if (ret < 0) { - /* here 'copied' is 0 due to previous checks */ - copied = ret; - break; - } - } - - if (unlikely(peek_seq != tp->copied_seq)) { - if (net_ratelimit()) - pr_info("TCP(%s:%d), race in MSG_PEEK.\n", - current->comm, current->pid); - peek_seq = tp->copied_seq; - } - continue; - -found_ok_skb: - avail = skb->len - offset; - if (len < avail) - avail = len; - /* - * Do we have urgent data here? We need to skip over the - * urgent byte. - */ - if (unlikely(tp->urg_data)) { - u32 urg_offset = tp->urg_seq - peek_seq; - - if (urg_offset < avail) { - /* - * The amount of data we are preparing to copy - * contains urgent data. - */ - if (!urg_offset) { /* First byte is urgent */ - if (!sock_flag(sk, SOCK_URGINLINE)) { - peek_seq++; - offset++; - avail--; - } - if (!avail) - continue; - } else { - /* stop short of the urgent data */ - avail = urg_offset; - } - } - } - - /* - * If MSG_TRUNC is specified the data is discarded. - */ - if (likely(!(flags & MSG_TRUNC))) - if (skb_copy_datagram_msg(skb, offset, msg, len)) { - if (!copied) { - copied = -EFAULT; - break; - } - } - peek_seq += avail; - copied += avail; - len -= avail; - } while (len > 0); - - release_sock(sk); - return copied; -} - -int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int flags) -{ - struct tcp_sock *tp = tcp_sk(sk); - struct chtls_sock *csk; - unsigned long avail; /* amount of available data in current skb */ - int buffers_freed; - int copied = 0; - long timeo; - int target; /* Read at least this many bytes */ - int ret; - - buffers_freed = 0; - - if (unlikely(flags & MSG_OOB)) - return tcp_prot.recvmsg(sk, msg, len, flags); - - if (unlikely(flags & MSG_PEEK)) - return peekmsg(sk, msg, len, flags); - - if (sk_can_busy_loop(sk) && - skb_queue_empty_lockless(&sk->sk_receive_queue) && - sk->sk_state == TCP_ESTABLISHED) - sk_busy_loop(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - csk = rcu_dereference_sk_user_data(sk); - - if (is_tls_rx(csk)) - return chtls_pt_recvmsg(sk, msg, len, flags); - - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - - if (unlikely(csk_flag(sk, CSK_UPDATE_RCV_WND))) - chtls_cleanup_rbuf(sk, copied); - - do { - struct sk_buff *skb; - u32 offset; - - if (unlikely(tp->urg_data && tp->urg_seq == tp->copied_seq)) { - if (copied) - break; - if (signal_pending(current)) { - copied = timeo ? sock_intr_errno(timeo) : - -EAGAIN; - break; - } - } - - skb = skb_peek(&sk->sk_receive_queue); - if (skb) - goto found_ok_skb; - - if (csk->wr_credits && - skb_queue_len(&csk->txq) && - chtls_push_frames(csk, csk->wr_credits == - csk->wr_max_credits)) - sk->sk_write_space(sk); - - if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) - break; - - if (copied) { - if (sk->sk_err || sk->sk_state == TCP_CLOSE || - (sk->sk_shutdown & RCV_SHUTDOWN) || - signal_pending(current)) - break; - } else { - if (sock_flag(sk, SOCK_DONE)) - break; - if (sk->sk_err) { - copied = sock_error(sk); - break; - } - if (sk->sk_shutdown & RCV_SHUTDOWN) - break; - if (sk->sk_state == TCP_CLOSE) { - copied = -ENOTCONN; - break; - } - if (!timeo) { - copied = -EAGAIN; - break; - } - if (signal_pending(current)) { - copied = sock_intr_errno(timeo); - break; - } - } - - if (READ_ONCE(sk->sk_backlog.tail)) { - release_sock(sk); - lock_sock(sk); - chtls_cleanup_rbuf(sk, copied); - continue; - } - - if (copied >= target) - break; - chtls_cleanup_rbuf(sk, copied); - ret = sk_wait_data(sk, &timeo, NULL); - if (ret < 0) { - copied = copied ? : ret; - goto unlock; - } - continue; - -found_ok_skb: - if (!skb->len) { - chtls_kfree_skb(sk, skb); - if (!copied && !timeo) { - copied = -EAGAIN; - break; - } - - if (copied < target) - continue; - - break; - } - - offset = tp->copied_seq - ULP_SKB_CB(skb)->seq; - avail = skb->len - offset; - if (len < avail) - avail = len; - - if (unlikely(tp->urg_data)) { - u32 urg_offset = tp->urg_seq - tp->copied_seq; - - if (urg_offset < avail) { - if (urg_offset) { - avail = urg_offset; - } else if (!sock_flag(sk, SOCK_URGINLINE)) { - tp->copied_seq++; - offset++; - avail--; - if (!avail) - goto skip_copy; - } - } - } - - if (likely(!(flags & MSG_TRUNC))) { - if (skb_copy_datagram_msg(skb, offset, - msg, avail)) { - if (!copied) { - copied = -EFAULT; - break; - } - } - } - - tp->copied_seq += avail; - copied += avail; - len -= avail; - -skip_copy: - if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) - tp->urg_data = 0; - - if (avail + offset >= skb->len) { - chtls_free_skb(sk, skb); - buffers_freed++; - - if (copied >= target && - !skb_peek(&sk->sk_receive_queue)) - break; - } - } while (len > 0); - - if (buffers_freed) - chtls_cleanup_rbuf(sk, copied); - -unlock: - release_sock(sk); - return copied; -} diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c deleted file mode 100644 index 2570575434f9..000000000000 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c +++ /dev/null @@ -1,642 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2018 Chelsio Communications, Inc. - * - * Written by: Atul Gupta (atul.gupta@chelsio.com) - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "chtls.h" -#include "chtls_cm.h" - -#define DRV_NAME "chtls" - -/* - * chtls device management - * maintains a list of the chtls devices - */ -static LIST_HEAD(cdev_list); -static DEFINE_MUTEX(cdev_mutex); - -static DEFINE_MUTEX(notify_mutex); -static RAW_NOTIFIER_HEAD(listen_notify_list); -static struct proto chtls_cpl_prot, chtls_cpl_protv6; -struct request_sock_ops chtls_rsk_ops, chtls_rsk_opsv6; -static uint send_page_order = (14 - PAGE_SHIFT < 0) ? 0 : 14 - PAGE_SHIFT; - -static void register_listen_notifier(struct notifier_block *nb) -{ - mutex_lock(¬ify_mutex); - raw_notifier_chain_register(&listen_notify_list, nb); - mutex_unlock(¬ify_mutex); -} - -static void unregister_listen_notifier(struct notifier_block *nb) -{ - mutex_lock(¬ify_mutex); - raw_notifier_chain_unregister(&listen_notify_list, nb); - mutex_unlock(¬ify_mutex); -} - -static int listen_notify_handler(struct notifier_block *this, - unsigned long event, void *data) -{ - struct chtls_listen *clisten; - int ret = NOTIFY_DONE; - - clisten = (struct chtls_listen *)data; - - switch (event) { - case CHTLS_LISTEN_START: - ret = chtls_listen_start(clisten->cdev, clisten->sk); - kfree(clisten); - break; - case CHTLS_LISTEN_STOP: - chtls_listen_stop(clisten->cdev, clisten->sk); - kfree(clisten); - break; - } - return ret; -} - -static struct notifier_block listen_notifier = { - .notifier_call = listen_notify_handler -}; - -static int listen_backlog_rcv(struct sock *sk, struct sk_buff *skb) -{ - if (likely(skb_transport_header(skb) != skb_network_header(skb))) - return tcp_v4_do_rcv(sk, skb); - BLOG_SKB_CB(skb)->backlog_rcv(sk, skb); - return 0; -} - -static int chtls_start_listen(struct chtls_dev *cdev, struct sock *sk) -{ - struct chtls_listen *clisten; - - if (sk->sk_protocol != IPPROTO_TCP) - return -EPROTONOSUPPORT; - - if (sk->sk_family == PF_INET && - LOOPBACK(inet_sk(sk)->inet_rcv_saddr)) - return -EADDRNOTAVAIL; - - sk->sk_backlog_rcv = listen_backlog_rcv; - clisten = kmalloc_obj(*clisten); - if (!clisten) - return -ENOMEM; - clisten->cdev = cdev; - clisten->sk = sk; - mutex_lock(¬ify_mutex); - raw_notifier_call_chain(&listen_notify_list, - CHTLS_LISTEN_START, clisten); - mutex_unlock(¬ify_mutex); - return 0; -} - -static void chtls_stop_listen(struct chtls_dev *cdev, struct sock *sk) -{ - struct chtls_listen *clisten; - - if (sk->sk_protocol != IPPROTO_TCP) - return; - - clisten = kmalloc_obj(*clisten); - if (!clisten) - return; - clisten->cdev = cdev; - clisten->sk = sk; - mutex_lock(¬ify_mutex); - raw_notifier_call_chain(&listen_notify_list, - CHTLS_LISTEN_STOP, clisten); - mutex_unlock(¬ify_mutex); -} - -static int chtls_inline_feature(struct tls_toe_device *dev) -{ - struct net_device *netdev; - struct chtls_dev *cdev; - int i; - - cdev = to_chtls_dev(dev); - - for (i = 0; i < cdev->lldi->nports; i++) { - netdev = cdev->ports[i]; - if (netdev->features & NETIF_F_HW_TLS_RECORD) - return 1; - } - return 0; -} - -static int chtls_create_hash(struct tls_toe_device *dev, struct sock *sk) -{ - struct chtls_dev *cdev = to_chtls_dev(dev); - - if (sk->sk_state == TCP_LISTEN) - return chtls_start_listen(cdev, sk); - return 0; -} - -static void chtls_destroy_hash(struct tls_toe_device *dev, struct sock *sk) -{ - struct chtls_dev *cdev = to_chtls_dev(dev); - - if (sk->sk_state == TCP_LISTEN) - chtls_stop_listen(cdev, sk); -} - -static void chtls_free_uld(struct chtls_dev *cdev) -{ - int i; - - tls_toe_unregister_device(&cdev->tlsdev); - kvfree(cdev->kmap.addr); - idr_destroy(&cdev->hwtid_idr); - for (i = 0; i < (1 << RSPQ_HASH_BITS); i++) - kfree_skb(cdev->rspq_skb_cache[i]); - kfree(cdev->lldi); - kfree_skb(cdev->askb); - kfree(cdev); -} - -static inline void chtls_dev_release(struct kref *kref) -{ - struct tls_toe_device *dev; - struct chtls_dev *cdev; - struct adapter *adap; - - dev = container_of(kref, struct tls_toe_device, kref); - cdev = to_chtls_dev(dev); - - /* Reset tls rx/tx stats */ - adap = pci_get_drvdata(cdev->pdev); - atomic_set(&adap->chcr_stats.tls_pdu_tx, 0); - atomic_set(&adap->chcr_stats.tls_pdu_rx, 0); - - chtls_free_uld(cdev); -} - -static void chtls_register_dev(struct chtls_dev *cdev) -{ - struct tls_toe_device *tlsdev = &cdev->tlsdev; - - strscpy(tlsdev->name, "chtls", TLS_TOE_DEVICE_NAME_MAX); - strlcat(tlsdev->name, cdev->lldi->ports[0]->name, - TLS_TOE_DEVICE_NAME_MAX); - tlsdev->feature = chtls_inline_feature; - tlsdev->hash = chtls_create_hash; - tlsdev->unhash = chtls_destroy_hash; - tlsdev->release = chtls_dev_release; - kref_init(&tlsdev->kref); - tls_toe_register_device(tlsdev); - cdev->cdev_state = CHTLS_CDEV_STATE_UP; -} - -static void process_deferq(struct work_struct *task_param) -{ - struct chtls_dev *cdev = container_of(task_param, - struct chtls_dev, deferq_task); - struct sk_buff *skb; - - spin_lock_bh(&cdev->deferq.lock); - while ((skb = __skb_dequeue(&cdev->deferq)) != NULL) { - spin_unlock_bh(&cdev->deferq.lock); - DEFERRED_SKB_CB(skb)->handler(cdev, skb); - spin_lock_bh(&cdev->deferq.lock); - } - spin_unlock_bh(&cdev->deferq.lock); -} - -static int chtls_get_skb(struct chtls_dev *cdev) -{ - cdev->askb = alloc_skb(sizeof(struct tcphdr), GFP_KERNEL); - if (!cdev->askb) - return -ENOMEM; - - skb_put(cdev->askb, sizeof(struct tcphdr)); - skb_reset_transport_header(cdev->askb); - memset(cdev->askb->data, 0, cdev->askb->len); - return 0; -} - -static void *chtls_uld_add(const struct cxgb4_lld_info *info) -{ - struct cxgb4_lld_info *lldi; - struct chtls_dev *cdev; - int i, j; - - cdev = kzalloc_obj(*cdev); - if (!cdev) - goto out; - - lldi = kzalloc_obj(*lldi); - if (!lldi) - goto out_lldi; - - if (chtls_get_skb(cdev)) - goto out_skb; - - *lldi = *info; - cdev->lldi = lldi; - cdev->pdev = lldi->pdev; - cdev->tids = lldi->tids; - cdev->ports = lldi->ports; - cdev->mtus = lldi->mtus; - cdev->tids = lldi->tids; - cdev->pfvf = FW_VIID_PFN_G(cxgb4_port_viid(lldi->ports[0])) - << FW_VIID_PFN_S; - - for (i = 0; i < (1 << RSPQ_HASH_BITS); i++) { - unsigned int size = 64 - sizeof(struct rsp_ctrl) - 8; - - cdev->rspq_skb_cache[i] = __alloc_skb(size, - gfp_any(), 0, - lldi->nodeid); - if (unlikely(!cdev->rspq_skb_cache[i])) - goto out_rspq_skb; - } - - idr_init(&cdev->hwtid_idr); - INIT_WORK(&cdev->deferq_task, process_deferq); - spin_lock_init(&cdev->listen_lock); - spin_lock_init(&cdev->idr_lock); - cdev->send_page_order = min_t(uint, get_order(32768), - send_page_order); - cdev->max_host_sndbuf = 48 * 1024; - - if (lldi->vr->key.size) - if (chtls_init_kmap(cdev, lldi)) - goto out_rspq_skb; - - mutex_lock(&cdev_mutex); - list_add_tail(&cdev->list, &cdev_list); - mutex_unlock(&cdev_mutex); - - return cdev; -out_rspq_skb: - for (j = 0; j < i; j++) - kfree_skb(cdev->rspq_skb_cache[j]); - kfree_skb(cdev->askb); -out_skb: - kfree(lldi); -out_lldi: - kfree(cdev); -out: - return NULL; -} - -static void chtls_free_all_uld(void) -{ - struct chtls_dev *cdev, *tmp; - - mutex_lock(&cdev_mutex); - list_for_each_entry_safe(cdev, tmp, &cdev_list, list) { - if (cdev->cdev_state == CHTLS_CDEV_STATE_UP) { - list_del(&cdev->list); - kref_put(&cdev->tlsdev.kref, cdev->tlsdev.release); - } - } - mutex_unlock(&cdev_mutex); -} - -static int chtls_uld_state_change(void *handle, enum cxgb4_state new_state) -{ - struct chtls_dev *cdev = handle; - - switch (new_state) { - case CXGB4_STATE_UP: - chtls_register_dev(cdev); - break; - case CXGB4_STATE_DOWN: - break; - case CXGB4_STATE_START_RECOVERY: - break; - case CXGB4_STATE_DETACH: - mutex_lock(&cdev_mutex); - list_del(&cdev->list); - mutex_unlock(&cdev_mutex); - kref_put(&cdev->tlsdev.kref, cdev->tlsdev.release); - break; - default: - break; - } - return 0; -} - -static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, - const __be64 *rsp, - u32 pktshift) -{ - struct sk_buff *skb; - - /* Allocate space for cpl_pass_accept_req which will be synthesized by - * driver. Once driver synthesizes cpl_pass_accept_req the skb will go - * through the regular cpl_pass_accept_req processing in TOM. - */ - skb = alloc_skb(size_add(gl->tot_len, - sizeof(struct cpl_pass_accept_req)) - - pktshift, GFP_ATOMIC); - if (unlikely(!skb)) - return NULL; - __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) - - pktshift); - /* For now we will copy cpl_rx_pkt in the skb */ - skb_copy_to_linear_data(skb, rsp, sizeof(struct cpl_rx_pkt)); - skb_copy_to_linear_data_offset(skb, sizeof(struct cpl_pass_accept_req) - , gl->va + pktshift, - gl->tot_len - pktshift); - - return skb; -} - -static int chtls_recv_packet(struct chtls_dev *cdev, - const struct pkt_gl *gl, const __be64 *rsp) -{ - unsigned int opcode = *(u8 *)rsp; - struct sk_buff *skb; - int ret; - - skb = copy_gl_to_skb_pkt(gl, rsp, cdev->lldi->sge_pktshift); - if (!skb) - return -ENOMEM; - - ret = chtls_handlers[opcode](cdev, skb); - if (ret & CPL_RET_BUF_DONE) - kfree_skb(skb); - - return 0; -} - -static int chtls_recv_rsp(struct chtls_dev *cdev, const __be64 *rsp) -{ - unsigned long rspq_bin; - unsigned int opcode; - struct sk_buff *skb; - unsigned int len; - int ret; - - len = 64 - sizeof(struct rsp_ctrl) - 8; - opcode = *(u8 *)rsp; - - rspq_bin = hash_ptr((void *)rsp, RSPQ_HASH_BITS); - skb = cdev->rspq_skb_cache[rspq_bin]; - if (skb && !skb_is_nonlinear(skb) && - !skb_shared(skb) && !skb_cloned(skb)) { - refcount_inc(&skb->users); - if (refcount_read(&skb->users) == 2) { - __skb_trim(skb, 0); - if (skb_tailroom(skb) >= len) - goto copy_out; - } - refcount_dec(&skb->users); - } - skb = alloc_skb(len, GFP_ATOMIC); - if (unlikely(!skb)) - return -ENOMEM; - -copy_out: - __skb_put(skb, len); - skb_copy_to_linear_data(skb, rsp, len); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - ret = chtls_handlers[opcode](cdev, skb); - - if (ret & CPL_RET_BUF_DONE) - kfree_skb(skb); - return 0; -} - -static void chtls_recv(struct chtls_dev *cdev, - struct sk_buff **skbs, const __be64 *rsp) -{ - struct sk_buff *skb = *skbs; - unsigned int opcode; - int ret; - - opcode = *(u8 *)rsp; - - __skb_push(skb, sizeof(struct rss_header)); - skb_copy_to_linear_data(skb, rsp, sizeof(struct rss_header)); - - ret = chtls_handlers[opcode](cdev, skb); - if (ret & CPL_RET_BUF_DONE) - kfree_skb(skb); -} - -static int chtls_uld_rx_handler(void *handle, const __be64 *rsp, - const struct pkt_gl *gl) -{ - struct chtls_dev *cdev = handle; - unsigned int opcode; - struct sk_buff *skb; - - opcode = *(u8 *)rsp; - - if (unlikely(opcode == CPL_RX_PKT)) { - if (chtls_recv_packet(cdev, gl, rsp) < 0) - goto nomem; - return 0; - } - - if (!gl) - return chtls_recv_rsp(cdev, rsp); - -#define RX_PULL_LEN 128 - skb = cxgb4_pktgl_to_skb(gl, RX_PULL_LEN, RX_PULL_LEN); - if (unlikely(!skb)) - goto nomem; - chtls_recv(cdev, &skb, rsp); - return 0; - -nomem: - return -ENOMEM; -} - -static int do_chtls_getsockopt(struct sock *sk, char __user *optval, - int __user *optlen) -{ - struct tls_crypto_info crypto_info = { 0 }; - - crypto_info.version = TLS_1_2_VERSION; - if (copy_to_user(optval, &crypto_info, sizeof(struct tls_crypto_info))) - return -EFAULT; - return 0; -} - -static int chtls_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - struct tls_context *ctx = tls_get_ctx(sk); - - if (level != SOL_TLS) - return ctx->sk_proto->getsockopt(sk, level, - optname, optval, optlen); - - return do_chtls_getsockopt(sk, optval, optlen); -} - -static int do_chtls_setsockopt(struct sock *sk, int optname, - sockptr_t optval, unsigned int optlen) -{ - struct tls_crypto_info *crypto_info, tmp_crypto_info; - struct chtls_sock *csk; - int keylen; - int cipher_type; - int rc = 0; - - csk = rcu_dereference_sk_user_data(sk); - - if (sockptr_is_null(optval) || optlen < sizeof(*crypto_info)) { - rc = -EINVAL; - goto out; - } - - rc = copy_from_sockptr(&tmp_crypto_info, optval, sizeof(*crypto_info)); - if (rc) { - rc = -EFAULT; - goto out; - } - - /* check version */ - if (tmp_crypto_info.version != TLS_1_2_VERSION) { - rc = -ENOTSUPP; - goto out; - } - - crypto_info = (struct tls_crypto_info *)&csk->tlshws.crypto_info; - - /* GCM mode of AES supports 128 and 256 bit encryption, so - * copy keys from user based on GCM cipher type. - */ - switch (tmp_crypto_info.cipher_type) { - case TLS_CIPHER_AES_GCM_128: { - /* Obtain version and type from previous copy */ - crypto_info[0] = tmp_crypto_info; - /* Now copy the following data */ - rc = copy_from_sockptr_offset((char *)crypto_info + - sizeof(*crypto_info), - optval, sizeof(*crypto_info), - sizeof(struct tls12_crypto_info_aes_gcm_128) - - sizeof(*crypto_info)); - - if (rc) { - rc = -EFAULT; - goto out; - } - - keylen = TLS_CIPHER_AES_GCM_128_KEY_SIZE; - cipher_type = TLS_CIPHER_AES_GCM_128; - break; - } - case TLS_CIPHER_AES_GCM_256: { - crypto_info[0] = tmp_crypto_info; - rc = copy_from_sockptr_offset((char *)crypto_info + - sizeof(*crypto_info), - optval, sizeof(*crypto_info), - sizeof(struct tls12_crypto_info_aes_gcm_256) - - sizeof(*crypto_info)); - - if (rc) { - rc = -EFAULT; - goto out; - } - - keylen = TLS_CIPHER_AES_GCM_256_KEY_SIZE; - cipher_type = TLS_CIPHER_AES_GCM_256; - break; - } - default: - rc = -EINVAL; - goto out; - } - rc = chtls_setkey(csk, keylen, optname, cipher_type); -out: - return rc; -} - -static int chtls_setsockopt(struct sock *sk, int level, int optname, - sockptr_t optval, unsigned int optlen) -{ - struct tls_context *ctx = tls_get_ctx(sk); - - if (level != SOL_TLS) - return ctx->sk_proto->setsockopt(sk, level, - optname, optval, optlen); - - return do_chtls_setsockopt(sk, optname, optval, optlen); -} - -static struct cxgb4_uld_info chtls_uld_info = { - .name = DRV_NAME, - .nrxq = MAX_ULD_QSETS, - .ntxq = MAX_ULD_QSETS, - .rxq_size = 1024, - .add = chtls_uld_add, - .state_change = chtls_uld_state_change, - .rx_handler = chtls_uld_rx_handler, -}; - -void chtls_install_cpl_ops(struct sock *sk) -{ - if (sk->sk_family == AF_INET) - sk->sk_prot = &chtls_cpl_prot; - else - sk->sk_prot = &chtls_cpl_protv6; -} - -static void __init chtls_init_ulp_ops(void) -{ - chtls_cpl_prot = tcp_prot; - chtls_init_rsk_ops(&chtls_cpl_prot, &chtls_rsk_ops, - &tcp_prot, PF_INET); - chtls_cpl_prot.close = chtls_close; - chtls_cpl_prot.disconnect = chtls_disconnect; - chtls_cpl_prot.destroy = chtls_destroy_sock; - chtls_cpl_prot.shutdown = chtls_shutdown; - chtls_cpl_prot.sendmsg = chtls_sendmsg; - chtls_cpl_prot.splice_eof = chtls_splice_eof; - chtls_cpl_prot.recvmsg = chtls_recvmsg; - chtls_cpl_prot.setsockopt = chtls_setsockopt; - chtls_cpl_prot.getsockopt = chtls_getsockopt; -#if IS_ENABLED(CONFIG_IPV6) - chtls_cpl_protv6 = chtls_cpl_prot; - chtls_init_rsk_ops(&chtls_cpl_protv6, &chtls_rsk_opsv6, - &tcpv6_prot, PF_INET6); -#endif -} - -static int __init chtls_register(void) -{ - chtls_init_ulp_ops(); - register_listen_notifier(&listen_notifier); - cxgb4_register_uld(CXGB4_ULD_TLS, &chtls_uld_info); - return 0; -} - -static void __exit chtls_unregister(void) -{ - unregister_listen_notifier(&listen_notifier); - chtls_free_all_uld(); - cxgb4_unregister_uld(CXGB4_ULD_TLS); -} - -module_init(chtls_register); -module_exit(chtls_unregister); - -MODULE_DESCRIPTION("Chelsio TLS Inline driver"); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Chelsio Communications"); -MODULE_VERSION(CHTLS_DRV_VERSION); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 93e4da7046a1..8eb6b8033606 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -79,7 +79,7 @@ enum { NETIF_F_HW_TLS_RX_BIT, /* Hardware TLS RX offload */ NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */ - NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */ + __UNUSED_NETIF_F_56, NETIF_F_GRO_FRAGLIST_BIT, /* Fraglist GRO */ NETIF_F_HW_MACSEC_BIT, /* Offload MACsec operations */ @@ -153,7 +153,6 @@ enum { #define NETIF_F_HW_ESP __NETIF_F(HW_ESP) #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) #define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) -#define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD) #define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4) #define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) #define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX) diff --git a/include/net/tls.h b/include/net/tls.h index 3811943288b3..e57bef58851e 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -85,7 +85,6 @@ enum { TLS_BASE, TLS_SW, TLS_HW, - TLS_HW_RECORD, TLS_NUM_CONFIG, }; diff --git a/include/net/tls_toe.h b/include/net/tls_toe.h deleted file mode 100644 index b3aa7593ce2c..000000000000 --- a/include/net/tls_toe.h +++ /dev/null @@ -1,77 +0,0 @@ -/* - * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. - * Copyright (c) 2016-2017, Dave Watson . All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include -#include - -struct sock; - -#define TLS_TOE_DEVICE_NAME_MAX 32 - -/* - * This structure defines the routines for Inline TLS driver. - * The following routines are optional and filled with a - * null pointer if not defined. - * - * @name: Its the name of registered Inline tls device - * @dev_list: Inline tls device list - * int (*feature)(struct tls_toe_device *device); - * Called to return Inline TLS driver capability - * - * int (*hash)(struct tls_toe_device *device, struct sock *sk); - * This function sets Inline driver for listen and program - * device specific functioanlity as required - * - * void (*unhash)(struct tls_toe_device *device, struct sock *sk); - * This function cleans listen state set by Inline TLS driver - * - * void (*release)(struct kref *kref); - * Release the registered device and allocated resources - * @kref: Number of reference to tls_toe_device - */ -struct tls_toe_device { - char name[TLS_TOE_DEVICE_NAME_MAX]; - struct list_head dev_list; - int (*feature)(struct tls_toe_device *device); - int (*hash)(struct tls_toe_device *device, struct sock *sk); - void (*unhash)(struct tls_toe_device *device, struct sock *sk); - void (*release)(struct kref *kref); - struct kref kref; -}; - -int tls_toe_bypass(struct sock *sk); -int tls_toe_hash(struct sock *sk); -void tls_toe_unhash(struct sock *sk); - -void tls_toe_register_device(struct tls_toe_device *device); -void tls_toe_unregister_device(struct tls_toe_device *device); diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index b8b9c42f848c..1245ab38afc1 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -203,6 +203,6 @@ enum { #define TLS_CONF_BASE 1 #define TLS_CONF_SW 2 #define TLS_CONF_HW 3 -#define TLS_CONF_HW_RECORD 4 +#define TLS_CONF_HW_RECORD 4 /* unused */ #endif /* _UAPI_LINUX_TLS_H */ diff --git a/net/ethtool/common.c b/net/ethtool/common.c index a24d3a8a9ec1..23db40618fed 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -67,7 +67,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_HW_ESP_BIT] = "esp-hw-offload", [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", - [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload", [NETIF_F_GRO_FRAGLIST_BIT] = "rx-gro-list", diff --git a/net/tls/Kconfig b/net/tls/Kconfig index a25bf57f2673..4f4d5973a28f 100644 --- a/net/tls/Kconfig +++ b/net/tls/Kconfig @@ -27,13 +27,3 @@ config TLS_DEVICE Enable kernel support for HW offload of the TLS protocol. If unsure, say N. - -config TLS_TOE - bool "Transport Layer Security TCP stack bypass" - depends on TLS - default n - help - Enable kernel support for legacy HW offload of the TLS protocol, - which is incompatible with the Linux networking stack semantics. - - If unsure, say N. diff --git a/net/tls/Makefile b/net/tls/Makefile index e41c800489ac..4c7d296081ee 100644 --- a/net/tls/Makefile +++ b/net/tls/Makefile @@ -9,5 +9,4 @@ obj-$(CONFIG_TLS) += tls.o tls-y := tls_main.o tls_sw.o tls_proc.o trace.o tls_strp.o -tls-$(CONFIG_TLS_TOE) += tls_toe.o tls-$(CONFIG_TLS_DEVICE) += tls_device.o tls_device_fallback.o diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index c10a3fd7fc17..13c88a7b8787 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -43,8 +43,6 @@ #include #include -#include - #include "tls.h" MODULE_AUTHOR("Mellanox Technologies"); @@ -963,9 +961,6 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG] ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ]; #endif -#ifdef CONFIG_TLS_TOE - ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base; -#endif } static void tls_build_proto(struct sock *sk) @@ -1037,11 +1032,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_HW][TLS_HW] = prot[TLS_HW][TLS_SW]; #endif -#ifdef CONFIG_TLS_TOE - prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; - prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_toe_hash; - prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_toe_unhash; -#endif } static int tls_init(struct sock *sk) @@ -1051,11 +1041,6 @@ static int tls_init(struct sock *sk) tls_build_proto(sk); -#ifdef CONFIG_TLS_TOE - if (tls_toe_bypass(sk)) - return 0; -#endif - /* The TLS ulp is currently supported only for TCP sockets * in ESTABLISHED state. * Supporting sockets in LISTEN state will require us @@ -1111,8 +1096,6 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx) return TLS_CONF_SW; case TLS_HW: return TLS_CONF_HW; - case TLS_HW_RECORD: - return TLS_CONF_HW_RECORD; } return 0; } diff --git a/net/tls/tls_toe.c b/net/tls/tls_toe.c deleted file mode 100644 index 825669e1ab47..000000000000 --- a/net/tls/tls_toe.c +++ /dev/null @@ -1,141 +0,0 @@ -/* - * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. - * Copyright (c) 2016-2017, Dave Watson . All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include -#include -#include -#include -#include -#include - -#include "tls.h" - -static LIST_HEAD(device_list); -static DEFINE_SPINLOCK(device_spinlock); - -static void tls_toe_sk_destruct(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct tls_context *ctx = tls_get_ctx(sk); - - ctx->sk_destruct(sk); - /* Free ctx */ - rcu_assign_pointer(icsk->icsk_ulp_data, NULL); - tls_ctx_free(sk, ctx); -} - -int tls_toe_bypass(struct sock *sk) -{ - struct tls_toe_device *dev; - struct tls_context *ctx; - int rc = 0; - - spin_lock_bh(&device_spinlock); - list_for_each_entry(dev, &device_list, dev_list) { - if (dev->feature && dev->feature(dev)) { - ctx = tls_ctx_create(sk); - if (!ctx) - goto out; - - ctx->sk_destruct = sk->sk_destruct; - sk->sk_destruct = tls_toe_sk_destruct; - ctx->rx_conf = TLS_HW_RECORD; - ctx->tx_conf = TLS_HW_RECORD; - update_sk_prot(sk, ctx); - rc = 1; - break; - } - } -out: - spin_unlock_bh(&device_spinlock); - return rc; -} - -void tls_toe_unhash(struct sock *sk) -{ - struct tls_context *ctx = tls_get_ctx(sk); - struct tls_toe_device *dev; - - spin_lock_bh(&device_spinlock); - list_for_each_entry(dev, &device_list, dev_list) { - if (dev->unhash) { - kref_get(&dev->kref); - spin_unlock_bh(&device_spinlock); - dev->unhash(dev, sk); - kref_put(&dev->kref, dev->release); - spin_lock_bh(&device_spinlock); - } - } - spin_unlock_bh(&device_spinlock); - ctx->sk_proto->unhash(sk); -} - -int tls_toe_hash(struct sock *sk) -{ - struct tls_context *ctx = tls_get_ctx(sk); - struct tls_toe_device *dev; - int err; - - err = ctx->sk_proto->hash(sk); - spin_lock_bh(&device_spinlock); - list_for_each_entry(dev, &device_list, dev_list) { - if (dev->hash) { - kref_get(&dev->kref); - spin_unlock_bh(&device_spinlock); - err |= dev->hash(dev, sk); - kref_put(&dev->kref, dev->release); - spin_lock_bh(&device_spinlock); - } - } - spin_unlock_bh(&device_spinlock); - - if (err) - tls_toe_unhash(sk); - return err; -} - -void tls_toe_register_device(struct tls_toe_device *device) -{ - spin_lock_bh(&device_spinlock); - list_add_tail(&device->dev_list, &device_list); - spin_unlock_bh(&device_spinlock); -} -EXPORT_SYMBOL(tls_toe_register_device); - -void tls_toe_unregister_device(struct tls_toe_device *device) -{ - spin_lock_bh(&device_spinlock); - list_del(&device->dev_list); - spin_unlock_bh(&device_spinlock); -} -EXPORT_SYMBOL(tls_toe_unregister_device); -- cgit v1.3-14-g43fede From 06c2dce2d0f69727144443664182052f56d1da35 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Mon, 8 Jun 2026 16:31:10 -0700 Subject: psp: add new netlink cmd for dev-assoc and dev-disassoc The main purpose of this cmd is to be able to associate a non-psp-capable device (e.g. veth or netkit) with a psp device. One use case is if we create a pair of veth/netkit, and assign 1 end inside a netns, while leaving the other end within the default netns, with a real PSP device, e.g. netdevsim or a physical PSP-capable NIC. With this command, we could associate the veth/netkit inside the netns with PSP device, so the virtual device could act as PSP-capable device to initiate PSP connections, and performs PSP encryption/decryption on the real PSP device. Signed-off-by: Wei Wang Reviewed-by: Daniel Zahka Link: https://patch.msgid.link/20260608233118.2694144-3-weibunny.kernel@gmail.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/psp.yaml | 69 +++++++- include/net/psp/types.h | 23 +++ include/uapi/linux/psp.h | 13 ++ net/psp/psp-nl-gen.c | 32 ++++ net/psp/psp-nl-gen.h | 2 + net/psp/psp.h | 1 + net/psp/psp_main.c | 15 ++ net/psp/psp_nl.c | 325 +++++++++++++++++++++++++++++++++-- 8 files changed, 469 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/psp.yaml b/Documentation/netlink/specs/psp.yaml index e3b0fe296e8f..aa79332cb9b1 100644 --- a/Documentation/netlink/specs/psp.yaml +++ b/Documentation/netlink/specs/psp.yaml @@ -13,6 +13,17 @@ definitions: hdr0-aes-gmac-128, hdr0-aes-gmac-256] attribute-sets: + - + name: assoc-dev-info + attributes: + - + name: ifindex + doc: ifindex of an associated network device. + type: u32 + - + name: nsid + doc: Network namespace ID of the associated device. + type: s32 - name: dev attributes: @@ -24,7 +35,9 @@ attribute-sets: min: 1 - name: ifindex - doc: ifindex of the main netdevice linked to the PSP device. + doc: | + ifindex of the main netdevice linked to the PSP device, + or the ifindex to associate with the PSP device. type: u32 - name: psp-versions-cap @@ -38,6 +51,28 @@ attribute-sets: type: u32 enum: version enum-as-flags: true + - + name: assoc-list + doc: List of associated virtual devices. + type: nest + nested-attributes: assoc-dev-info + multi-attr: true + - + name: nsid + doc: | + Network namespace ID for the device to associate/disassociate. + Optional for dev-assoc and dev-disassoc; if not present, the + device is looked up in the caller's network namespace. + type: s32 + - + name: by-association + doc: | + Flag indicating the PSP device is an associated device from a + different network namespace. + Present when in associated namespace, absent when in primary/host + namespace. + type: flag + - name: assoc attributes: @@ -170,6 +205,8 @@ operations: - ifindex - psp-versions-cap - psp-versions-ena + - assoc-list + - by-association pre: psp-device-get-locked post: psp-device-unlock dump: @@ -281,6 +318,36 @@ operations: post: psp-device-unlock dump: reply: *stats-all + - + name: dev-assoc + doc: Associate a network device with a PSP device. + attribute-set: dev + flags: [admin-perm] + do: + request: + attributes: + - id + - ifindex + - nsid + reply: + attributes: [] + pre: psp-device-get-locked + post: psp-device-unlock + - + name: dev-disassoc + doc: Disassociate a network device from a PSP device. + attribute-set: dev + flags: [admin-perm] + do: + request: + attributes: + - id + - ifindex + - nsid + reply: + attributes: [] + pre: psp-device-get-locked + post: psp-device-unlock mcast-groups: list: diff --git a/include/net/psp/types.h b/include/net/psp/types.h index 25a9096d4e7d..87991a1ea02d 100644 --- a/include/net/psp/types.h +++ b/include/net/psp/types.h @@ -5,6 +5,7 @@ #include #include +#include struct netlink_ext_ack; @@ -43,9 +44,29 @@ struct psp_dev_config { u32 versions; }; +/* Max number of devices that can be associated with a single PSP device. + * Each entry consumes ~24 bytes in the netlink dev-get response, and the + * response must fit in GENLMSG_DEFAULT_SIZE (~3.7KB). + */ +#define PSP_ASSOC_DEV_MAX 128 + +/** + * struct psp_assoc_dev - wrapper for associated net_device + * @dev_list: list node for psp_dev::assoc_dev_list + * @assoc_dev: the associated net_device + * @dev_tracker: tracker for the net_device reference + */ +struct psp_assoc_dev { + struct list_head dev_list; + struct net_device *assoc_dev; + netdevice_tracker dev_tracker; +}; + /** * struct psp_dev - PSP device struct * @main_netdev: original netdevice of this PSP device + * @assoc_dev_list: list of psp_assoc_dev entries associated with this PSP device + * @assoc_dev_cnt: number of entries in @assoc_dev_list * @ops: driver callbacks * @caps: device capabilities * @drv_priv: driver priv pointer @@ -67,6 +88,8 @@ struct psp_dev_config { */ struct psp_dev { struct net_device *main_netdev; + struct list_head assoc_dev_list; + int assoc_dev_cnt; struct psp_dev_ops *ops; struct psp_dev_caps *caps; diff --git a/include/uapi/linux/psp.h b/include/uapi/linux/psp.h index a3a336488dc3..1c8899cd4da5 100644 --- a/include/uapi/linux/psp.h +++ b/include/uapi/linux/psp.h @@ -17,11 +17,22 @@ enum psp_version { PSP_VERSION_HDR0_AES_GMAC_256, }; +enum { + PSP_A_ASSOC_DEV_INFO_IFINDEX = 1, + PSP_A_ASSOC_DEV_INFO_NSID, + + __PSP_A_ASSOC_DEV_INFO_MAX, + PSP_A_ASSOC_DEV_INFO_MAX = (__PSP_A_ASSOC_DEV_INFO_MAX - 1) +}; + enum { PSP_A_DEV_ID = 1, PSP_A_DEV_IFINDEX, PSP_A_DEV_PSP_VERSIONS_CAP, PSP_A_DEV_PSP_VERSIONS_ENA, + PSP_A_DEV_ASSOC_LIST, + PSP_A_DEV_NSID, + PSP_A_DEV_BY_ASSOCIATION, __PSP_A_DEV_MAX, PSP_A_DEV_MAX = (__PSP_A_DEV_MAX - 1) @@ -74,6 +85,8 @@ enum { PSP_CMD_RX_ASSOC, PSP_CMD_TX_ASSOC, PSP_CMD_GET_STATS, + PSP_CMD_DEV_ASSOC, + PSP_CMD_DEV_DISASSOC, __PSP_CMD_MAX, PSP_CMD_MAX = (__PSP_CMD_MAX - 1) diff --git a/net/psp/psp-nl-gen.c b/net/psp/psp-nl-gen.c index a71dd629aeab..c3cc189f0a7b 100644 --- a/net/psp/psp-nl-gen.c +++ b/net/psp/psp-nl-gen.c @@ -53,6 +53,20 @@ static const struct nla_policy psp_get_stats_nl_policy[PSP_A_STATS_DEV_ID + 1] = [PSP_A_STATS_DEV_ID] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* PSP_CMD_DEV_ASSOC - do */ +static const struct nla_policy psp_dev_assoc_nl_policy[PSP_A_DEV_NSID + 1] = { + [PSP_A_DEV_ID] = NLA_POLICY_MIN(NLA_U32, 1), + [PSP_A_DEV_IFINDEX] = { .type = NLA_U32, }, + [PSP_A_DEV_NSID] = { .type = NLA_S32, }, +}; + +/* PSP_CMD_DEV_DISASSOC - do */ +static const struct nla_policy psp_dev_disassoc_nl_policy[PSP_A_DEV_NSID + 1] = { + [PSP_A_DEV_ID] = NLA_POLICY_MIN(NLA_U32, 1), + [PSP_A_DEV_IFINDEX] = { .type = NLA_U32, }, + [PSP_A_DEV_NSID] = { .type = NLA_S32, }, +}; + /* Ops table for psp */ static const struct genl_split_ops psp_nl_ops[] = { { @@ -119,6 +133,24 @@ static const struct genl_split_ops psp_nl_ops[] = { .dumpit = psp_nl_get_stats_dumpit, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = PSP_CMD_DEV_ASSOC, + .pre_doit = psp_device_get_locked, + .doit = psp_nl_dev_assoc_doit, + .post_doit = psp_device_unlock, + .policy = psp_dev_assoc_nl_policy, + .maxattr = PSP_A_DEV_NSID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = PSP_CMD_DEV_DISASSOC, + .pre_doit = psp_device_get_locked, + .doit = psp_nl_dev_disassoc_doit, + .post_doit = psp_device_unlock, + .policy = psp_dev_disassoc_nl_policy, + .maxattr = PSP_A_DEV_NSID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group psp_nl_mcgrps[] = { diff --git a/net/psp/psp-nl-gen.h b/net/psp/psp-nl-gen.h index 977355455395..4dd0f0f23053 100644 --- a/net/psp/psp-nl-gen.h +++ b/net/psp/psp-nl-gen.h @@ -33,6 +33,8 @@ int psp_nl_rx_assoc_doit(struct sk_buff *skb, struct genl_info *info); int psp_nl_tx_assoc_doit(struct sk_buff *skb, struct genl_info *info); int psp_nl_get_stats_doit(struct sk_buff *skb, struct genl_info *info); int psp_nl_get_stats_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int psp_nl_dev_assoc_doit(struct sk_buff *skb, struct genl_info *info); +int psp_nl_dev_disassoc_doit(struct sk_buff *skb, struct genl_info *info); enum { PSP_NLGRP_MGMT, diff --git a/net/psp/psp.h b/net/psp/psp.h index 0f9c4e4e52cb..cf381e786cb6 100644 --- a/net/psp/psp.h +++ b/net/psp/psp.h @@ -15,6 +15,7 @@ extern struct mutex psp_devs_lock; void psp_dev_free(struct psp_dev *psd); int psp_dev_check_access(struct psp_dev *psd, struct net *net, bool admin); +bool psp_has_assoc_dev_in_ns(struct psp_dev *psd, struct net *net); void psp_nl_notify_dev(struct psp_dev *psd, u32 cmd); diff --git a/net/psp/psp_main.c b/net/psp/psp_main.c index aaa44e6cb9ff..470f6c7ce9ee 100644 --- a/net/psp/psp_main.c +++ b/net/psp/psp_main.c @@ -39,6 +39,10 @@ int psp_dev_check_access(struct psp_dev *psd, struct net *net, bool admin) { if (dev_net(psd->main_netdev) == net) return 0; + + if (!admin && psp_has_assoc_dev_in_ns(psd, net)) + return 0; + return -ENOENT; } @@ -74,6 +78,7 @@ psp_dev_create(struct net_device *netdev, return ERR_PTR(-ENOMEM); psd->main_netdev = netdev; + INIT_LIST_HEAD(&psd->assoc_dev_list); psd->ops = psd_ops; psd->caps = psd_caps; psd->drv_priv = priv_ptr; @@ -125,6 +130,7 @@ void psp_dev_free(struct psp_dev *psd) */ void psp_dev_unregister(struct psp_dev *psd) { + struct psp_assoc_dev *entry, *entry_tmp; struct psp_assoc *pas, *next; mutex_lock(&psp_devs_lock); @@ -144,6 +150,15 @@ void psp_dev_unregister(struct psp_dev *psd) list_for_each_entry_safe(pas, next, &psd->stale_assocs, assocs_list) psp_dev_tx_key_del(psd, pas); + list_for_each_entry_safe(entry, entry_tmp, &psd->assoc_dev_list, + dev_list) { + list_del(&entry->dev_list); + rcu_assign_pointer(entry->assoc_dev->psp_dev, NULL); + netdev_put(entry->assoc_dev, &entry->dev_tracker); + kfree(entry); + } + psd->assoc_dev_cnt = 0; + rcu_assign_pointer(psd->main_netdev->psp_dev, NULL); psd->ops = NULL; diff --git a/net/psp/psp_nl.c b/net/psp/psp_nl.c index b4f1b7f9b0c2..a2058aaf0f36 100644 --- a/net/psp/psp_nl.c +++ b/net/psp/psp_nl.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include #include #include #include @@ -38,6 +39,74 @@ static int psp_nl_reply_send(struct sk_buff *rsp, struct genl_info *info) return genlmsg_reply(rsp, info); } +/** + * psp_nl_multicast_per_ns() - multicast a notification to each unique netns + * @psd: PSP device (must be locked) + * @group: multicast group + * @build_ntf: callback to build an skb for a given netns, or NULL on failure + * @ctx: opaque context passed to @build_ntf + * + * Iterates all unique network namespaces from the associated device list + * plus the main device's netns. For each unique netns, calls @build_ntf + * to construct a notification skb and multicasts it. + */ +static void +psp_nl_multicast_per_ns(struct psp_dev *psd, unsigned int group, + struct sk_buff *(*build_ntf)(struct psp_dev *, + struct net *, + void *), + void *ctx) +{ + struct psp_assoc_dev *entry; + struct xarray sent_nets; + struct net *main_net; + struct sk_buff *ntf; + + main_net = dev_net(psd->main_netdev); + xa_init(&sent_nets); + + list_for_each_entry(entry, &psd->assoc_dev_list, dev_list) { + struct net *assoc_net = dev_net(entry->assoc_dev); + int ret; + + if (net_eq(assoc_net, main_net)) + continue; + + ret = xa_insert(&sent_nets, (unsigned long)assoc_net, assoc_net, + GFP_KERNEL); + if (ret == -EBUSY) + continue; + + ntf = build_ntf(psd, assoc_net, ctx); + if (!ntf) + continue; + + genlmsg_multicast_netns(&psp_nl_family, assoc_net, ntf, 0, + group, GFP_KERNEL); + } + xa_destroy(&sent_nets); + + /* Send to main device netns */ + ntf = build_ntf(psd, main_net, ctx); + if (!ntf) + return; + genlmsg_multicast_netns(&psp_nl_family, main_net, ntf, 0, group, + GFP_KERNEL); +} + +static struct sk_buff *psp_nl_clone_ntf(struct psp_dev *psd, struct net *net, + void *ctx) +{ + return skb_clone(ctx, GFP_KERNEL); +} + +static void psp_nl_multicast_all_ns(struct psp_dev *psd, struct sk_buff *ntf, + unsigned int group) +{ + psp_nl_multicast_per_ns(psd, group, psp_nl_clone_ntf, ntf); + nlmsg_consume(ntf); +} + /* Device stuff */ static struct psp_dev * @@ -91,6 +160,38 @@ int psp_device_get_locked(const struct genl_split_ops *ops, return __psp_device_get_locked(ops, skb, info, false); } +static struct net *psp_nl_resolve_assoc_dev_ns(struct psp_dev *psd, + struct genl_info *info) +{ + struct net *net; + int nsid; + + if (GENL_REQ_ATTR_CHECK(info, PSP_A_DEV_IFINDEX)) + return ERR_PTR(-EINVAL); + + if (info->attrs[PSP_A_DEV_NSID]) { + /* Only callers in the main netns may specify nsid */ + if (dev_net(psd->main_netdev) != genl_info_net(info)) { + NL_SET_BAD_ATTR(info->extack, + info->attrs[PSP_A_DEV_NSID]); + return ERR_PTR(-EPERM); + } + + nsid = nla_get_s32(info->attrs[PSP_A_DEV_NSID]); + + net = get_net_ns_by_id(genl_info_net(info), nsid); + if (!net) { + NL_SET_BAD_ATTR(info->extack, + info->attrs[PSP_A_DEV_NSID]); + return ERR_PTR(-EINVAL); + } + } else { + net = get_net(genl_info_net(info)); + } + + return net; +} + void psp_device_unlock(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) @@ -103,11 +204,67 @@ psp_device_unlock(const struct genl_split_ops *ops, struct sk_buff *skb, sockfd_put(socket); } +bool psp_has_assoc_dev_in_ns(struct psp_dev *psd, struct net *net) +{ + struct psp_assoc_dev *entry; + + list_for_each_entry(entry, &psd->assoc_dev_list, dev_list) { + if (dev_net(entry->assoc_dev) == net) + return true; + } + + return false; +} + +static int psp_nl_fill_assoc_dev_list(struct psp_dev *psd, struct sk_buff *rsp, + struct net *cur_net, + struct net *filter_net) +{ + struct psp_assoc_dev *entry; + struct net *dev_net_ns; + struct nlattr *nest; + int nsid; + + list_for_each_entry(entry, &psd->assoc_dev_list, dev_list) { + dev_net_ns = dev_net(entry->assoc_dev); + + if (filter_net && dev_net_ns != filter_net) + continue; + + /* When filtering by namespace, all devices are in the caller's + * namespace so nsid is always NETNSA_NSID_NOT_ASSIGNED (-1). + * Otherwise, calculate the nsid relative to cur_net. + */ + nsid = filter_net ? NETNSA_NSID_NOT_ASSIGNED : + peernet2id_alloc(cur_net, dev_net_ns, + GFP_KERNEL); + + nest = nla_nest_start(rsp, PSP_A_DEV_ASSOC_LIST); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(rsp, PSP_A_ASSOC_DEV_INFO_IFINDEX, + entry->assoc_dev->ifindex) || + nla_put_s32(rsp, PSP_A_ASSOC_DEV_INFO_NSID, nsid)) { + nla_nest_cancel(rsp, nest); + return -EMSGSIZE; + } + + nla_nest_end(rsp, nest); + } + + return 0; +} + static int psp_nl_dev_fill(struct psp_dev *psd, struct sk_buff *rsp, const struct genl_info *info) { + struct net *cur_net; void *hdr; + int err; + + cur_net = genl_info_net(info); hdr = genlmsg_iput(rsp, info); if (!hdr) @@ -119,6 +276,22 @@ psp_nl_dev_fill(struct psp_dev *psd, struct sk_buff *rsp, nla_put_u32(rsp, PSP_A_DEV_PSP_VERSIONS_ENA, psd->config.versions)) goto err_cancel_msg; + if (cur_net == dev_net(psd->main_netdev)) { + /* Primary device - dump assoc list */ + err = psp_nl_fill_assoc_dev_list(psd, rsp, cur_net, NULL); + if (err) + goto err_cancel_msg; + } else { + /* In netns: set by-association flag and dump filtered + * assoc list containing only devices in cur_net + */ + if (nla_put_flag(rsp, PSP_A_DEV_BY_ASSOCIATION)) + goto err_cancel_msg; + err = psp_nl_fill_assoc_dev_list(psd, rsp, cur_net, cur_net); + if (err) + goto err_cancel_msg; + } + genlmsg_end(rsp, hdr); return 0; @@ -127,27 +300,34 @@ err_cancel_msg: return -EMSGSIZE; } -void psp_nl_notify_dev(struct psp_dev *psd, u32 cmd) +static struct sk_buff *psp_nl_build_dev_ntf(struct psp_dev *psd, + struct net *net, void *ctx) { + u32 cmd = *(u32 *)ctx; struct genl_info info; struct sk_buff *ntf; - if (!genl_has_listeners(&psp_nl_family, dev_net(psd->main_netdev), - PSP_NLGRP_MGMT)) - return; + if (!genl_has_listeners(&psp_nl_family, net, PSP_NLGRP_MGMT)) + return NULL; ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ntf) - return; + return NULL; genl_info_init_ntf(&info, &psp_nl_family, cmd); + genl_info_net_set(&info, net); if (psp_nl_dev_fill(psd, ntf, &info)) { nlmsg_free(ntf); - return; + return NULL; } - genlmsg_multicast_netns(&psp_nl_family, dev_net(psd->main_netdev), ntf, - 0, PSP_NLGRP_MGMT, GFP_KERNEL); + return ntf; +} + +void psp_nl_notify_dev(struct psp_dev *psd, u32 cmd) +{ + psp_nl_multicast_per_ns(psd, PSP_NLGRP_MGMT, + psp_nl_build_dev_ntf, &cmd); } int psp_nl_dev_get_doit(struct sk_buff *req, struct genl_info *info) @@ -281,8 +461,9 @@ int psp_nl_key_rotate_doit(struct sk_buff *skb, struct genl_info *info) psd->stats.rotations++; nlmsg_end(ntf, (struct nlmsghdr *)ntf->data); - genlmsg_multicast_netns(&psp_nl_family, dev_net(psd->main_netdev), ntf, - 0, PSP_NLGRP_USE, GFP_KERNEL); + + psp_nl_multicast_all_ns(psd, ntf, PSP_NLGRP_USE); + return psp_nl_reply_send(rsp, info); err_free_ntf: @@ -292,6 +473,130 @@ err_free_rsp: return err; } +int psp_nl_dev_assoc_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct psp_dev *psd = info->user_ptr[0]; + struct psp_assoc_dev *psp_assoc_dev; + struct net_device *assoc_dev; + struct sk_buff *rsp; + u32 assoc_ifindex; + struct net *net; + int err; + + if (psd->assoc_dev_cnt >= PSP_ASSOC_DEV_MAX) { + NL_SET_ERR_MSG(info->extack, + "Maximum number of associated devices reached"); + return -ENOSPC; + } + + net = psp_nl_resolve_assoc_dev_ns(psd, info); + if (IS_ERR(net)) + return PTR_ERR(net); + + psp_assoc_dev = kzalloc_obj(*psp_assoc_dev); + if (!psp_assoc_dev) { + err = -ENOMEM; + goto err_put_net; + } + + assoc_ifindex = nla_get_u32(info->attrs[PSP_A_DEV_IFINDEX]); + assoc_dev = netdev_get_by_index(net, assoc_ifindex, + &psp_assoc_dev->dev_tracker, + GFP_KERNEL); + if (!assoc_dev) { + NL_SET_BAD_ATTR(info->extack, info->attrs[PSP_A_DEV_IFINDEX]); + err = -ENODEV; + goto err_free_assoc; + } + + /* Check if device is already associated with a PSP device */ + if (cmpxchg(&assoc_dev->psp_dev, NULL, RCU_INITIALIZER(psd))) { + NL_SET_ERR_MSG(info->extack, + "Device already associated with a PSP device"); + err = -EBUSY; + goto err_put_dev; + } + + psp_assoc_dev->assoc_dev = assoc_dev; + rsp = psp_nl_reply_new(info); + if (!rsp) { + err = -ENOMEM; + goto err_clean_ptr; + } + + list_add_tail(&psp_assoc_dev->dev_list, &psd->assoc_dev_list); + psd->assoc_dev_cnt++; + + put_net(net); + + psp_nl_notify_dev(psd, PSP_CMD_DEV_CHANGE_NTF); + + return psp_nl_reply_send(rsp, info); + +err_clean_ptr: + rcu_assign_pointer(assoc_dev->psp_dev, NULL); +err_put_dev: + netdev_put(assoc_dev, &psp_assoc_dev->dev_tracker); +err_free_assoc: + kfree(psp_assoc_dev); +err_put_net: + put_net(net); + + return err; +} + +int psp_nl_dev_disassoc_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct psp_assoc_dev *entry, *found = NULL; + struct psp_dev *psd = info->user_ptr[0]; + struct sk_buff *rsp; + u32 assoc_ifindex; + struct net *net; + + net = psp_nl_resolve_assoc_dev_ns(psd, info); + if (IS_ERR(net)) + return PTR_ERR(net); + + assoc_ifindex = nla_get_u32(info->attrs[PSP_A_DEV_IFINDEX]); + + /* Search the association list by ifindex and netns */ + list_for_each_entry(entry, &psd->assoc_dev_list, dev_list) { + if (entry->assoc_dev->ifindex == assoc_ifindex && + dev_net(entry->assoc_dev) == net) { + found = entry; + break; + } + } + + if (!found) { + put_net(net); + NL_SET_BAD_ATTR(info->extack, info->attrs[PSP_A_DEV_IFINDEX]); + return -ENODEV; + } + + rsp = psp_nl_reply_new(info); + if (!rsp) { + put_net(net); + return -ENOMEM; + } + + put_net(net); + + /* Notify before removal so listeners in the disassociated namespace + * still receive the notification. + */ + psp_nl_notify_dev(psd, PSP_CMD_DEV_CHANGE_NTF); + + /* Remove from the association list */ + list_del(&found->dev_list); + psd->assoc_dev_cnt--; + rcu_assign_pointer(found->assoc_dev->psp_dev, NULL); + netdev_put(found->assoc_dev, &found->dev_tracker); + kfree(found); + + return psp_nl_reply_send(rsp, info); +} + /* Key etc. */ int psp_assoc_device_get_locked(const struct genl_split_ops *ops, -- cgit v1.3-14-g43fede From 9375487c0c78817b3651e2621d648c6198757c41 Mon Sep 17 00:00:00 2001 From: Grzegorz Nitka Date: Sun, 7 Jun 2026 20:30:33 +0200 Subject: dpll: add generic DPLL type Add DPLL_TYPE_GENERIC to represent DPLL devices which do not fit the existing PPS or EEC classes. The UAPI type is intentionally generic. During netdev discussion, maintainers pointed out that introducing identifiers tied to a specific placement or single design does not scale across ASICs and vendors. The role of a DPLL is already inferable from the spawning driver, bus device, and pin topology, without encoding additional purpose-specific taxonomy in the type name. Using a generic type keeps the UAPI extensible and avoids premature naming that may become incorrect as new hardware topologies are exposed through the DPLL subsystem. Expose the new type through UAPI and netlink specification as "generic". Reviewed-by: Aleksandr Loktionov Reviewed-by: Jiri Pirko Signed-off-by: Grzegorz Nitka Link: https://patch.msgid.link/20260607183045.1213735-2-grzegorz.nitka@intel.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/dpll.yaml | 3 +++ drivers/dpll/dpll_nl.c | 2 +- include/uapi/linux/dpll.h | 2 ++ 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 91a172617b3a..2bf83f6732ab 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -138,6 +138,9 @@ definitions: - name: eec doc: dpll drives the Ethernet Equipment Clock + - + name: generic + doc: generic dpll type for devices outside PPS/EEC classes render-max: true - type: enum diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index b1d9182c7802..ed3bbe9841ea 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -37,7 +37,7 @@ const struct nla_policy dpll_reference_sync_nl_policy[DPLL_A_PIN_STATE + 1] = { static const struct nla_policy dpll_device_id_get_nl_policy[DPLL_A_TYPE + 1] = { [DPLL_A_MODULE_NAME] = { .type = NLA_NUL_STRING, }, [DPLL_A_CLOCK_ID] = { .type = NLA_U64, }, - [DPLL_A_TYPE] = NLA_POLICY_RANGE(NLA_U32, 1, 2), + [DPLL_A_TYPE] = NLA_POLICY_RANGE(NLA_U32, 1, 3), }; /* DPLL_CMD_DEVICE_GET - do */ diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index cb363cccf2e2..55eaa82f5f98 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -109,10 +109,12 @@ enum dpll_clock_quality_level { * enum dpll_type - type of dpll, valid values for DPLL_A_TYPE attribute * @DPLL_TYPE_PPS: dpll produces Pulse-Per-Second signal * @DPLL_TYPE_EEC: dpll drives the Ethernet Equipment Clock + * @DPLL_TYPE_GENERIC: generic dpll type for devices outside PPS/EEC classes */ enum dpll_type { DPLL_TYPE_PPS = 1, DPLL_TYPE_EEC, + DPLL_TYPE_GENERIC, /* private: */ __DPLL_TYPE_MAX, -- cgit v1.3-14-g43fede From 9a8ed15ce22472fe0363e33738b4317d06b13c3a Mon Sep 17 00:00:00 2001 From: Matthieu Buffet Date: Thu, 11 Jun 2026 18:21:01 +0200 Subject: landlock: Add UDP bind() access control MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for a first fine-grained UDP access right. LANDLOCK_ACCESS_NET_BIND_UDP controls the ability to set the local port of a UDP socket (via bind()). It will be useful for servers (to start receiving datagrams), and for some clients that need to use a specific source port (e.g. mDNS requires to use port 5353) For obvious performance concerns, access control is only enforced when configuring sockets, not when using them for common send/recv operations. Bump ABI to allow userspace to detect and use this new right. Signed-off-by: Matthieu Buffet Link: https://patch.msgid.link/20260611162107.49278-2-matthieu@buffet.re [mic: Fix comment formatting] Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 14 ++++++++++---- security/landlock/audit.c | 1 + security/landlock/limits.h | 2 +- security/landlock/net.c | 18 ++++++++++++------ security/landlock/syscalls.c | 2 +- tools/testing/selftests/landlock/base_test.c | 4 ++-- tools/testing/selftests/landlock/net_test.c | 5 +++-- 7 files changed, 30 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 10a346e55e95..f2927681e92d 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -200,10 +200,10 @@ struct landlock_net_port_attr { * (also used for IPv6), and within that range, on a per-socket basis * with ``setsockopt(IP_LOCAL_PORT_RANGE)``. * - * A Landlock rule with port 0 and the %LANDLOCK_ACCESS_NET_BIND_TCP - * right means that requesting to bind on port 0 is allowed and it will - * automatically translate to binding on a kernel-assigned ephemeral - * port. + * A Landlock rule with port 0 and the %LANDLOCK_ACCESS_NET_BIND_TCP or + * %LANDLOCK_ACCESS_NET_BIND_UDP right means that requesting to bind on + * port 0 is allowed and it will automatically translate to binding on a + * kernel-assigned ephemeral port. */ __u64 port; }; @@ -373,10 +373,16 @@ struct landlock_net_port_attr { * port. Support added in Landlock ABI version 4. * - %LANDLOCK_ACCESS_NET_CONNECT_TCP: Connect TCP sockets to the given * remote port. Support added in Landlock ABI version 4. + * + * And similarly for UDP port numbers: + * + * - %LANDLOCK_ACCESS_NET_BIND_UDP: Bind UDP sockets to the given local + * port. Support added in Landlock ABI version 10. */ /* clang-format off */ #define LANDLOCK_ACCESS_NET_BIND_TCP (1ULL << 0) #define LANDLOCK_ACCESS_NET_CONNECT_TCP (1ULL << 1) +#define LANDLOCK_ACCESS_NET_BIND_UDP (1ULL << 2) /* clang-format on */ /** diff --git a/security/landlock/audit.c b/security/landlock/audit.c index 8d0edf94037d..e676ebffeebe 100644 --- a/security/landlock/audit.c +++ b/security/landlock/audit.c @@ -45,6 +45,7 @@ static_assert(ARRAY_SIZE(fs_access_strings) == LANDLOCK_NUM_ACCESS_FS); static const char *const net_access_strings[] = { [BIT_INDEX(LANDLOCK_ACCESS_NET_BIND_TCP)] = "net.bind_tcp", [BIT_INDEX(LANDLOCK_ACCESS_NET_CONNECT_TCP)] = "net.connect_tcp", + [BIT_INDEX(LANDLOCK_ACCESS_NET_BIND_UDP)] = "net.bind_udp", }; static_assert(ARRAY_SIZE(net_access_strings) == LANDLOCK_NUM_ACCESS_NET); diff --git a/security/landlock/limits.h b/security/landlock/limits.h index b454ad73b15e..c0f30a4591b8 100644 --- a/security/landlock/limits.h +++ b/security/landlock/limits.h @@ -23,7 +23,7 @@ #define LANDLOCK_MASK_ACCESS_FS ((LANDLOCK_LAST_ACCESS_FS << 1) - 1) #define LANDLOCK_NUM_ACCESS_FS __const_hweight64(LANDLOCK_MASK_ACCESS_FS) -#define LANDLOCK_LAST_ACCESS_NET LANDLOCK_ACCESS_NET_CONNECT_TCP +#define LANDLOCK_LAST_ACCESS_NET LANDLOCK_ACCESS_NET_BIND_UDP #define LANDLOCK_MASK_ACCESS_NET ((LANDLOCK_LAST_ACCESS_NET << 1) - 1) #define LANDLOCK_NUM_ACCESS_NET __const_hweight64(LANDLOCK_MASK_ACCESS_NET) diff --git a/security/landlock/net.c b/security/landlock/net.c index 4ee4002a8f56..f57fe2a44f0d 100644 --- a/security/landlock/net.c +++ b/security/landlock/net.c @@ -88,15 +88,17 @@ static int current_check_access_socket(struct socket *const sock, * inconsistencies and return -EINVAL if needed. */ return 0; - } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { + } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP || + access_request == LANDLOCK_ACCESS_NET_BIND_UDP) { /* * Binding to an AF_UNSPEC address is treated * differently by IPv4 and IPv6 sockets. The socket's * family may change under our feet due to * setsockopt(IPV6_ADDRFORM), but that's ok: we either - * reject entirely or require - * %LANDLOCK_ACCESS_NET_BIND_TCP for the given port, so - * it cannot be used to bypass the policy. + * reject entirely for IPv6 or require + * %LANDLOCK_ACCESS_NET_BIND_TCP or + * %LANDLOCK_ACCESS_NET_BIND_UDP for IPv4, so it cannot + * be used to bypass the policy. * * IPv4 sockets map AF_UNSPEC to AF_INET for * retrocompatibility for bind accesses, only if the @@ -142,7 +144,8 @@ static int current_check_access_socket(struct socket *const sock, if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) { audit_net.dport = port; audit_net.v4info.daddr = addr4->sin_addr.s_addr; - } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { + } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP || + access_request == LANDLOCK_ACCESS_NET_BIND_UDP) { audit_net.sport = port; audit_net.v4info.saddr = addr4->sin_addr.s_addr; } else { @@ -164,7 +167,8 @@ static int current_check_access_socket(struct socket *const sock, if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) { audit_net.dport = port; audit_net.v6info.daddr = addr6->sin6_addr; - } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { + } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP || + access_request == LANDLOCK_ACCESS_NET_BIND_UDP) { audit_net.sport = port; audit_net.v6info.saddr = addr6->sin6_addr; } else { @@ -224,6 +228,8 @@ static int hook_socket_bind(struct socket *const sock, if (sk_is_tcp(sock->sk)) access_request = LANDLOCK_ACCESS_NET_BIND_TCP; + else if (sk_is_udp(sock->sk)) + access_request = LANDLOCK_ACCESS_NET_BIND_UDP; else return 0; diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index accfd2e5a0cd..d45469d5d464 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -166,7 +166,7 @@ static const struct file_operations ruleset_fops = { * If the change involves a fix that requires userspace awareness, also update * the errata documentation in Documentation/userspace-api/landlock.rst . */ -const int landlock_abi_version = 9; +const int landlock_abi_version = 10; /** * sys_landlock_create_ruleset - Create a new ruleset diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c index 30d37234086c..6c8113c2ded1 100644 --- a/tools/testing/selftests/landlock/base_test.c +++ b/tools/testing/selftests/landlock/base_test.c @@ -76,8 +76,8 @@ TEST(abi_version) const struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, }; - ASSERT_EQ(9, landlock_create_ruleset(NULL, 0, - LANDLOCK_CREATE_RULESET_VERSION)); + ASSERT_EQ(10, landlock_create_ruleset(NULL, 0, + LANDLOCK_CREATE_RULESET_VERSION)); ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0, LANDLOCK_CREATE_RULESET_VERSION)); diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 0c256e7c8675..135b09fd1880 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -1326,11 +1326,12 @@ FIXTURE_TEARDOWN(mini) /* clang-format off */ -#define ACCESS_LAST LANDLOCK_ACCESS_NET_CONNECT_TCP +#define ACCESS_LAST LANDLOCK_ACCESS_NET_BIND_UDP #define ACCESS_ALL ( \ LANDLOCK_ACCESS_NET_BIND_TCP | \ - LANDLOCK_ACCESS_NET_CONNECT_TCP) + LANDLOCK_ACCESS_NET_CONNECT_TCP | \ + LANDLOCK_ACCESS_NET_BIND_UDP) /* clang-format on */ -- cgit v1.3-14-g43fede From e61247a2e694d17236149135b2d22f0f7d19578c Mon Sep 17 00:00:00 2001 From: Matthieu Buffet Date: Thu, 11 Jun 2026 18:21:02 +0200 Subject: landlock: Add UDP send+connect access control MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for a second fine-grained UDP access right. LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP controls the ability to set the remote port of a socket (via connect()) and to specify an explicit destination when sending a datagram, to override any remote peer set on a UDP socket (e.g. in sendto() or sendmsg()). It will be useful for applications that send datagrams, and for some servers too (those creating per-client sockets, which want to receive traffic only from a specific address). Similarly as for bind(), this access control is performed when configuring sockets, not in hot code paths. Add detection of when autobind is about to be required, and deny the operation if the process would not be allowed to call bind(0) explicitly. Autobind can only be performed in udp_lib_get_port() from code paths already controlled by LSM hooks: when connect()ing, sending a first datagram, and in some splice() EOF edge case which, afaiu, can only happen after a remote peer has been set. This invariant needs to be preserved to keep bind policies actually enforced. Signed-off-by: Matthieu Buffet Link: https://patch.msgid.link/20260611162107.49278-3-matthieu@buffet.re [mic: Add quick return for non-sandboxed tasks, fix sa_family dereferencing, fix comment formatting] Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 23 +++++ security/landlock/audit.c | 2 + security/landlock/limits.h | 2 +- security/landlock/net.c | 148 ++++++++++++++++++++++++---- tools/testing/selftests/landlock/net_test.c | 5 +- 5 files changed, 160 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index f2927681e92d..811ec77f9105 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -378,11 +378,34 @@ struct landlock_net_port_attr { * * - %LANDLOCK_ACCESS_NET_BIND_UDP: Bind UDP sockets to the given local * port. Support added in Landlock ABI version 10. + * - %LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP: Set the remote port of UDP + * sockets to the given port, or send datagrams to the given remote port + * ignoring any destination pre-set on a socket. Support added in + * Landlock ABI version 10. + * + * .. note:: Setting a remote address or sending a first datagram + * auto-binds UDP sockets to an ephemeral local source port if not + * already bound. To allow this if both %LANDLOCK_ACCESS_NET_BIND_UDP + * and %LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP are handled, you need to + * either: + * + * - use a socket already bound to a port before the ruleset started + * being enforced; + * - or grant %LANDLOCK_ACCESS_NET_BIND_UDP on port 0, meaning "any + * port in the ephemeral port range"; + * - or grant %LANDLOCK_ACCESS_NET_BIND_UDP on a specific port, and + * call :manpage:`bind(2)` on that port before trying to + * :manpage:`connect(2)` or send datagrams. + * + * .. note:: Sending datagrams to an ``AF_UNSPEC`` destination address + * family is not supported for IPv6 UDP sockets: you will need to use a + * ``NULL`` address instead. */ /* clang-format off */ #define LANDLOCK_ACCESS_NET_BIND_TCP (1ULL << 0) #define LANDLOCK_ACCESS_NET_CONNECT_TCP (1ULL << 1) #define LANDLOCK_ACCESS_NET_BIND_UDP (1ULL << 2) +#define LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP (1ULL << 3) /* clang-format on */ /** diff --git a/security/landlock/audit.c b/security/landlock/audit.c index e676ebffeebe..851647197a01 100644 --- a/security/landlock/audit.c +++ b/security/landlock/audit.c @@ -46,6 +46,8 @@ static const char *const net_access_strings[] = { [BIT_INDEX(LANDLOCK_ACCESS_NET_BIND_TCP)] = "net.bind_tcp", [BIT_INDEX(LANDLOCK_ACCESS_NET_CONNECT_TCP)] = "net.connect_tcp", [BIT_INDEX(LANDLOCK_ACCESS_NET_BIND_UDP)] = "net.bind_udp", + [BIT_INDEX(LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP)] = + "net.connect_send_udp", }; static_assert(ARRAY_SIZE(net_access_strings) == LANDLOCK_NUM_ACCESS_NET); diff --git a/security/landlock/limits.h b/security/landlock/limits.h index c0f30a4591b8..a4d908b240a2 100644 --- a/security/landlock/limits.h +++ b/security/landlock/limits.h @@ -23,7 +23,7 @@ #define LANDLOCK_MASK_ACCESS_FS ((LANDLOCK_LAST_ACCESS_FS << 1) - 1) #define LANDLOCK_NUM_ACCESS_FS __const_hweight64(LANDLOCK_MASK_ACCESS_FS) -#define LANDLOCK_LAST_ACCESS_NET LANDLOCK_ACCESS_NET_BIND_UDP +#define LANDLOCK_LAST_ACCESS_NET LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP #define LANDLOCK_MASK_ACCESS_NET ((LANDLOCK_LAST_ACCESS_NET << 1) - 1) #define LANDLOCK_NUM_ACCESS_NET __const_hweight64(LANDLOCK_MASK_ACCESS_NET) diff --git a/security/landlock/net.c b/security/landlock/net.c index f57fe2a44f0d..942f856433c9 100644 --- a/security/landlock/net.c +++ b/security/landlock/net.c @@ -44,7 +44,8 @@ int landlock_append_net_rule(struct landlock_ruleset *const ruleset, static int current_check_access_socket(struct socket *const sock, struct sockaddr *const address, const int addrlen, - access_mask_t access_request) + access_mask_t access_request, + bool connecting) { unsigned short sock_family; __be16 port; @@ -75,19 +76,50 @@ static int current_check_access_socket(struct socket *const sock, switch (address->sa_family) { case AF_UNSPEC: - if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) { + if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP || + (access_request == LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP && + connecting)) { /* - * Connecting to an address with AF_UNSPEC dissolves - * the TCP association, which have the same effect as - * closing the connection while retaining the socket - * object (i.e., the file descriptor). As for dropping - * privileges, closing connections is always allowed. - * - * For a TCP access control system, this request is - * legitimate. Let the network stack handle potential - * inconsistencies and return -EINVAL if needed. + * Connecting to an address with AF_UNSPEC dissolves the + * remote association while retaining the socket object + * (i.e., the file descriptor). For TCP, it has the same + * effect as closing the connection. For UDP, it removes + * any preset remote address. As for dropping + * privileges, these actions are always allowed. Let + * the network stack handle potential inconsistencies + * and return -EINVAL if needed. */ return 0; + } else if (access_request == + LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP) { + if (sock_family == AF_INET6) { + /* + * We cannot allow sending UDP datagrams to an + * explicit AF_UNSPEC address on IPv6 sockets, + * even if AF_UNSPEC is treated as "no address" + * on such sockets (so it should always be + * allowed). That's because the socket's family + * can change under our feet (if another thread + * calls setsockopt(IPV6_ADDRFORM)) to IPv4, + * which would then treat AF_UNSPEC as AF_INET. + */ + audit_net.family = AF_UNSPEC; + audit_net.sk = sock->sk; + landlock_init_layer_masks( + subject->domain, access_request, + &layer_masks, LANDLOCK_KEY_NET_PORT); + landlock_log_denial( + subject, + &(struct landlock_request){ + .type = LANDLOCK_REQUEST_NET_ACCESS, + .audit.type = + LSM_AUDIT_DATA_NET, + .audit.u.net = &audit_net, + .access = access_request, + .layer_masks = &layer_masks, + }); + return -EACCES; + } } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP || access_request == LANDLOCK_ACCESS_NET_BIND_UDP) { /* @@ -130,7 +162,11 @@ static int current_check_access_socket(struct socket *const sock, } else { WARN_ON_ONCE(1); } - /* Only for bind(AF_UNSPEC+INADDR_ANY) on IPv4 socket. */ + /* + * AF_UNSPEC is treated as AF_INET only in + * bind(AF_UNSPEC+INADDR_ANY) on IPv4 sockets and when sending + * to AF_UNSPEC addresses on IPv4 sockets. + */ fallthrough; case AF_INET: { const struct sockaddr_in *addr4; @@ -141,7 +177,8 @@ static int current_check_access_socket(struct socket *const sock, addr4 = (struct sockaddr_in *)address; port = addr4->sin_port; - if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) { + if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP || + access_request == LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP) { audit_net.dport = port; audit_net.v4info.daddr = addr4->sin_addr.s_addr; } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP || @@ -164,7 +201,8 @@ static int current_check_access_socket(struct socket *const sock, addr6 = (struct sockaddr_in6 *)address; port = addr6->sin6_port; - if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) { + if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP || + access_request == LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP) { audit_net.dport = port; audit_net.v6info.daddr = addr6->sin6_addr; } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP || @@ -221,6 +259,44 @@ static int current_check_access_socket(struct socket *const sock, return -EACCES; } +static int current_check_autobind_udp_socket(struct socket *const sock) +{ + const struct access_masks bind_udp = { + .net = LANDLOCK_ACCESS_NET_BIND_UDP, + }; + struct sockaddr_storage port0 = {}; + unsigned short num; + bool slow; + + /* Quick return for non-Landlocked tasks. */ + if (!landlock_get_applicable_subject(current_cred(), bind_udp, NULL)) + return 0; + + /* + * On UDP sockets, if a local port has not already been bound, calling + * connect() or sending a first datagram has the side effect of + * autobinding an ephemeral port: we also have to check that the process + * would have had the right to bind(0) explicitly. Hold the socket lock + * around the inet_num read to exclude udp_lib_get_port()'s transient + * inet_num = snum write that is reverted to 0 on a failing reuseport + * bind. + */ + slow = lock_sock_fast(sock->sk); + num = inet_sk(sock->sk)->inet_num; + unlock_sock_fast(sock->sk, slow); + if (num != 0) + return 0; + + /* + * Construct a struct sockaddr* with port 0 to pretend the process tried + * to bind() on that address. + */ + port0.ss_family = READ_ONCE(sock->sk->sk_family); + + return current_check_access_socket(sock, (struct sockaddr *)&port0, + sizeof(port0), bind_udp.net, false); +} + static int hook_socket_bind(struct socket *const sock, struct sockaddr *const address, const int addrlen) { @@ -234,7 +310,7 @@ static int hook_socket_bind(struct socket *const sock, return 0; return current_check_access_socket(sock, address, addrlen, - access_request); + access_request, false); } static int hook_socket_connect(struct socket *const sock, @@ -242,19 +318,57 @@ static int hook_socket_connect(struct socket *const sock, const int addrlen) { access_mask_t access_request; + int ret = 0; if (sk_is_tcp(sock->sk)) access_request = LANDLOCK_ACCESS_NET_CONNECT_TCP; + else if (sk_is_udp(sock->sk)) + access_request = LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP; else return 0; - return current_check_access_socket(sock, address, addrlen, - access_request); + ret = current_check_access_socket(sock, address, addrlen, + access_request, true); + + /* + * connect()ing to an AF_UNSPEC address does not trigger an autobind and + * should never be restricted. + */ + if (ret == 0 && sk_is_udp(sock->sk) && + addrlen >= offsetofend(typeof(*address), sa_family) && + address->sa_family != AF_UNSPEC) + ret = current_check_autobind_udp_socket(sock); + + return ret; +} + +static int hook_socket_sendmsg(struct socket *const sock, + struct msghdr *const msg, const int size) +{ + struct sockaddr *const address = msg->msg_name; + const int addrlen = msg->msg_namelen; + access_mask_t access_request; + int ret = 0; + + if (sk_is_udp(sock->sk)) + access_request = LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP; + else + return 0; + + if (address != NULL) + ret = current_check_access_socket(sock, address, addrlen, + access_request, false); + + if (ret == 0) + ret = current_check_autobind_udp_socket(sock); + + return ret; } static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(socket_bind, hook_socket_bind), LSM_HOOK_INIT(socket_connect, hook_socket_connect), + LSM_HOOK_INIT(socket_sendmsg, hook_socket_sendmsg), }; __init void landlock_add_net_hooks(void) diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 135b09fd1880..23d860e76372 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -1326,12 +1326,13 @@ FIXTURE_TEARDOWN(mini) /* clang-format off */ -#define ACCESS_LAST LANDLOCK_ACCESS_NET_BIND_UDP +#define ACCESS_LAST LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP #define ACCESS_ALL ( \ LANDLOCK_ACCESS_NET_BIND_TCP | \ LANDLOCK_ACCESS_NET_CONNECT_TCP | \ - LANDLOCK_ACCESS_NET_BIND_UDP) + LANDLOCK_ACCESS_NET_BIND_UDP | \ + LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP) /* clang-format on */ -- cgit v1.3-14-g43fede From eb7b4d458e0d6833ffbb717edf4282f5ca6a7b57 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 9 Jun 2026 09:34:48 +0530 Subject: devlink: Implement devlink param multi attribute nested data values Devlink param value attribute is not defined since devlink is handling the value validating and parsing internally, this allows us to implement multi attribute values without breaking any policies. Devlink param multi-attribute values are considered to be dynamically sized arrays of u64 values, by introducing a new devlink param type DEVLINK_PARAM_TYPE_U64_ARRAY, driver and user space can set a variable count of u64 values into the DEVLINK_ATTR_PARAM_VALUE_DATA attribute. Implement get/set parsing and add to the internal value structure passed to drivers. This is useful for devices that need to configure a list of values for a specific configuration. example: $ devlink dev param show pci/... name multi-value-param name multi-value-param type driver-specific values: cmode permanent value: 0,1,2,3,4,5,6,7 $ devlink dev param set pci/... name multi-value-param \ value 4,5,6,7,0,1,2,3 cmode permanent Signed-off-by: Saeed Mahameed Signed-off-by: Ratheesh Kannoth Link: https://patch.msgid.link/20260609040453.711932-5-rkannoth@marvell.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/devlink.yaml | 4 ++++ include/net/devlink.h | 8 ++++++++ include/uapi/linux/devlink.h | 1 + net/devlink/netlink_gen.c | 2 ++ net/devlink/param.c | 33 +++++++++++++++++++++++++++++++- 5 files changed, 47 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 247b147d689f..52ad1e7805d1 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -234,6 +234,10 @@ definitions: value: 10 - name: binary + - + name: u64-array + value: 129 + - name: rate-tc-index-max type: const diff --git a/include/net/devlink.h b/include/net/devlink.h index 5f4083dc4345..dd546dbd57cf 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -433,6 +433,13 @@ enum devlink_param_type { DEVLINK_PARAM_TYPE_U64 = DEVLINK_VAR_ATTR_TYPE_U64, DEVLINK_PARAM_TYPE_STRING = DEVLINK_VAR_ATTR_TYPE_STRING, DEVLINK_PARAM_TYPE_BOOL = DEVLINK_VAR_ATTR_TYPE_FLAG, + DEVLINK_PARAM_TYPE_U64_ARRAY = DEVLINK_VAR_ATTR_TYPE_U64_ARRAY, +}; + +#define __DEVLINK_PARAM_MAX_ARRAY_SIZE 32 +struct devlink_param_u64_array { + u64 size; + u64 val[__DEVLINK_PARAM_MAX_ARRAY_SIZE]; }; union devlink_param_value { @@ -442,6 +449,7 @@ union devlink_param_value { u64 vu64; char vstr[__DEVLINK_PARAM_MAX_STRING_VALUE]; bool vbool; + struct devlink_param_u64_array u64arr; }; struct devlink_param_gset_ctx { diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 0b165eac7619..ca713bcc47b9 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -406,6 +406,7 @@ enum devlink_var_attr_type { DEVLINK_VAR_ATTR_TYPE_BINARY, __DEVLINK_VAR_ATTR_TYPE_CUSTOM_BASE = 0x80, /* Any possible custom types, unrelated to NLA_* values go below */ + DEVLINK_VAR_ATTR_TYPE_U64_ARRAY, }; enum devlink_attr { diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index 81899786fd98..f52b0c2b19ed 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -37,6 +37,8 @@ devlink_attr_param_type_validate(const struct nlattr *attr, case DEVLINK_VAR_ATTR_TYPE_NUL_STRING: fallthrough; case DEVLINK_VAR_ATTR_TYPE_BINARY: + fallthrough; + case DEVLINK_VAR_ATTR_TYPE_U64_ARRAY: return 0; } NL_SET_ERR_MSG_ATTR(extack, attr, "invalid enum value"); diff --git a/net/devlink/param.c b/net/devlink/param.c index bd3881349c60..3e9d2e5750c2 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -252,6 +252,15 @@ devlink_nl_param_value_put(struct sk_buff *msg, enum devlink_param_type type, return -EMSGSIZE; } break; + case DEVLINK_PARAM_TYPE_U64_ARRAY: + if (val->u64arr.size > __DEVLINK_PARAM_MAX_ARRAY_SIZE) + return -EMSGSIZE; + + for (int i = 0; i < val->u64arr.size; i++) { + if (nla_put_uint(msg, nla_type, val->u64arr.val[i])) + return -EMSGSIZE; + } + break; } return 0; } @@ -537,7 +546,7 @@ devlink_param_value_get_from_info(const struct devlink_param *param, union devlink_param_value *value) { struct nlattr *param_data; - int len; + int len, cnt, rem; param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]; @@ -577,6 +586,28 @@ devlink_param_value_get_from_info(const struct devlink_param *param, return -EINVAL; value->vbool = nla_get_flag(param_data); break; + + case DEVLINK_PARAM_TYPE_U64_ARRAY: + cnt = 0; + nla_for_each_attr_type(param_data, + DEVLINK_ATTR_PARAM_VALUE_DATA, + genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + if (cnt >= __DEVLINK_PARAM_MAX_ARRAY_SIZE) + return -EMSGSIZE; + + if ((nla_len(param_data) != sizeof(u64)) && + (nla_len(param_data) != sizeof(u32))) { + NL_SET_BAD_ATTR(info->extack, param_data); + return -EINVAL; + } + + value->u64arr.val[cnt] = nla_get_uint(param_data); + cnt++; + } + + value->u64arr.size = cnt; + break; } return 0; } -- cgit v1.3-14-g43fede From 29752205db5ff1793437b352c9e343b8e41fb184 Mon Sep 17 00:00:00 2001 From: Tingmao Wang Date: Fri, 12 Jun 2026 02:48:48 +0100 Subject: landlock: Add API support and docs for the quiet flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds the UAPI for the quiet flags feature (but not the implementation yet). Even though currently LANDLOCK_ADD_RULE_QUIET only affects audit logging, in the future this can also be used as part of a supervisor mechanism, where it will also suppress denial notifications on a per-object basis. Thus the name is deliberately generic, as opposed to e.g. LANDLOCK_ADD_RULE_LOG_QUIET. According to pahole, even after adding the struct access_masks quiet_masks in struct landlock_hierarchy, the u32 log_* bitfield still only has a size of 2 bytes, so there's minimal wasted space. Assisted-by: GitHub-Copilot:claude-opus-4.8 Signed-off-by: Tingmao Wang [mic: Update date, fix comment formatting] Link: https://patch.msgid.link/031184748a8e74c0bb02f1fa13d7a3f10918c627.1781228815.git.m@maowtm.org Signed-off-by: Mickaël Salaün --- Documentation/admin-guide/LSM/landlock.rst | 9 ++-- Documentation/userspace-api/landlock.rst | 14 ++++++ include/uapi/linux/landlock.h | 60 +++++++++++++++++++++++ security/landlock/domain.h | 5 ++ security/landlock/fs.c | 4 +- security/landlock/fs.h | 2 +- security/landlock/net.c | 5 +- security/landlock/net.h | 5 +- security/landlock/ruleset.c | 12 ++++- security/landlock/ruleset.h | 12 +++-- security/landlock/syscalls.c | 71 +++++++++++++++++++++------- tools/testing/selftests/landlock/base_test.c | 2 +- 12 files changed, 170 insertions(+), 31 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/LSM/landlock.rst b/Documentation/admin-guide/LSM/landlock.rst index 2dacb381c1a9..314052bbeb0a 100644 --- a/Documentation/admin-guide/LSM/landlock.rst +++ b/Documentation/admin-guide/LSM/landlock.rst @@ -19,8 +19,10 @@ Audit Denied access requests are logged by default for a sandboxed program if `audit` is enabled. This default behavior can be changed with the sys_landlock_restrict_self() flags (cf. -Documentation/userspace-api/landlock.rst). Landlock logs can also be masked -thanks to audit rules. Landlock can generate 2 audit record types. +Documentation/userspace-api/landlock.rst), or suppressed on a per-object +basis by using ``LANDLOCK_ADD_RULE_QUIET`` (ABI 10+). Landlock logs can +also be masked thanks to audit rules. Landlock can generate 2 audit +record types. Record types ------------ @@ -174,7 +176,8 @@ If you get spammed with audit logs related to Landlock, this is either an attack attempt or a bug in the security policy. We can put in place some filters to limit noise with two complementary ways: -- with sys_landlock_restrict_self()'s flags if we can fix the sandboxed +- with sys_landlock_restrict_self()'s flags, or + ``LANDLOCK_ADD_RULE_QUIET`` (ABI 10+) if we can fix the sandboxed programs, - or with audit rules (see :manpage:`auditctl(8)`). diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst index b5a2ab6f4766..5a63d4476c1c 100644 --- a/Documentation/userspace-api/landlock.rst +++ b/Documentation/userspace-api/landlock.rst @@ -775,6 +775,20 @@ remote port of UDP sockets (via :manpage:`connect(2)`), and sending datagrams to an explicit remote port (ignoring any destination set on UDP sockets, via e.g. :manpage:`sendto(2)`). +Quiet rule flag (ABI < 10) +-------------------------- + +Starting with the Landlock ABI version 10, it is possible to selectively +suppress logs for specific denied accesses on a per-object basis with +the ``LANDLOCK_ADD_RULE_QUIET`` flag of sys_landlock_add_rule(), in +combination with the ``quiet_access_fs`` and ``quiet_access_net`` fields +of struct landlock_ruleset_attr. It is also now possible to suppress +logs for scope accesses via the ``quiet_scoped`` field of struct +landlock_ruleset_attr. The object is marked as quiet within a ruleset +when at least one sys_landlock_add_rule() call is made for it with the +``LANDLOCK_ADD_RULE_QUIET`` flag, additional add-rule calls for the same +object without this flag do not clear it. + .. _kernel_support: Kernel support diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 811ec77f9105..7ffe2ef127ee 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -32,6 +32,19 @@ * *handle* a wide range or all access rights that they know about at build time * (and that they have tested with a kernel that supported them all). * + * @quiet_access_fs and @quiet_access_net are bitmasks of actions for which a + * denial by this layer will not trigger a log if the corresponding object (or + * its children, for filesystem rules) is marked with the "quiet" bit via + * %LANDLOCK_ADD_RULE_QUIET, even if logging would normally take place per + * landlock_restrict_self() flags. @quiet_scoped is similar, except that it + * does not require marking any objects as quiet - if the ruleset is created + * with any bits set in @quiet_scoped, then denial of such scoped resources will + * not trigger any log. These 3 fields are available since Landlock ABI version + * 10. + * + * @quiet_access_fs, @quiet_access_net and @quiet_scoped must be a subset of + * @handled_access_fs, @handled_access_net and @scoped respectively. + * * This structure can grow in future Landlock versions. */ struct landlock_ruleset_attr { @@ -51,6 +64,20 @@ struct landlock_ruleset_attr { * resources (e.g. IPCs). */ __u64 scoped; + /** + * @quiet_access_fs: Bitmask of filesystem actions which should not be + * logged if per-object quiet flag is set. + */ + __u64 quiet_access_fs; + /** + * @quiet_access_net: Bitmask of network actions which should not be + * logged if per-object quiet flag is set. + */ + __u64 quiet_access_net; + /** + * @quiet_scoped: Bitmask of scoped actions which should not be logged. + */ + __u64 quiet_scoped; }; /** @@ -69,6 +96,39 @@ struct landlock_ruleset_attr { #define LANDLOCK_CREATE_RULESET_ERRATA (1U << 1) /* clang-format on */ +/** + * DOC: landlock_add_rule_flags + * + * **Flags** + * + * %LANDLOCK_ADD_RULE_QUIET + * Together with the quiet_* fields in struct landlock_ruleset_attr, + * this flag controls whether Landlock will log audit messages when + * access to the objects covered by this rule is denied by this layer. + * + * If logging is enabled, when Landlock denies an access, it will + * suppress the log if all of the following are true: + * + * - this layer is the innermost layer that denied the access; + * - all accesses denied by this layer are part of the quiet_* fields + * in the related struct landlock_ruleset_attr; + * - the object (or one of its parents, for filesystem rules) is + * marked as "quiet" via %LANDLOCK_ADD_RULE_QUIET. + * + * Because logging is only suppressed by a layer if the layer denies + * access, a sandboxed program cannot use this flag to "hide" access + * denials, without denying itself the access in the first place. + * + * The effect of this flag does not depend on the value of + * allowed_access in the passed in rule_attr. When this flag is + * present, the caller is also allowed to pass in an empty + * allowed_access. + */ + +/* clang-format off */ +#define LANDLOCK_ADD_RULE_QUIET (1U << 0) +/* clang-format on */ + /** * DOC: landlock_restrict_self_flags * diff --git a/security/landlock/domain.h b/security/landlock/domain.h index af100a8cd939..9f560f3c3bd1 100644 --- a/security/landlock/domain.h +++ b/security/landlock/domain.h @@ -111,6 +111,11 @@ struct landlock_hierarchy { * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON. Set to false by default. */ log_new_exec : 1; + /** + * @quiet_masks: Bitmasks of access that should be quieted (i.e. not + * logged) if the related object is marked as quiet. + */ + struct access_masks quiet_masks; #endif /* CONFIG_AUDIT */ }; diff --git a/security/landlock/fs.c b/security/landlock/fs.c index d7cd2d5c9057..bd68a752abbf 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -325,7 +325,7 @@ retry: */ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, const struct path *const path, - access_mask_t access_rights) + access_mask_t access_rights, const u32 flags) { int err; struct landlock_id id = { @@ -346,7 +346,7 @@ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, if (IS_ERR(id.key.object)) return PTR_ERR(id.key.object); mutex_lock(&ruleset->lock); - err = landlock_insert_rule(ruleset, id, access_rights); + err = landlock_insert_rule(ruleset, id, access_rights, flags); mutex_unlock(&ruleset->lock); /* * No need to check for an error because landlock_insert_rule() diff --git a/security/landlock/fs.h b/security/landlock/fs.h index 911b83669e20..e4c530511360 100644 --- a/security/landlock/fs.h +++ b/security/landlock/fs.h @@ -136,6 +136,6 @@ __init void landlock_add_fs_hooks(void); int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, const struct path *const path, - access_mask_t access_hierarchy); + access_mask_t access_hierarchy, const u32 flags); #endif /* _SECURITY_LANDLOCK_FS_H */ diff --git a/security/landlock/net.c b/security/landlock/net.c index d7a4d116f7ee..cbff59ec3aba 100644 --- a/security/landlock/net.c +++ b/security/landlock/net.c @@ -20,7 +20,8 @@ #include "ruleset.h" int landlock_append_net_rule(struct landlock_ruleset *const ruleset, - const u16 port, access_mask_t access_rights) + const u16 port, access_mask_t access_rights, + const u32 flags) { int err; const struct landlock_id id = { @@ -35,7 +36,7 @@ int landlock_append_net_rule(struct landlock_ruleset *const ruleset, ~landlock_get_net_access_mask(ruleset, 0); mutex_lock(&ruleset->lock); - err = landlock_insert_rule(ruleset, id, access_rights); + err = landlock_insert_rule(ruleset, id, access_rights, flags); mutex_unlock(&ruleset->lock); return err; diff --git a/security/landlock/net.h b/security/landlock/net.h index 09960c237a13..5c0e3b4090cb 100644 --- a/security/landlock/net.h +++ b/security/landlock/net.h @@ -16,7 +16,8 @@ __init void landlock_add_net_hooks(void); int landlock_append_net_rule(struct landlock_ruleset *const ruleset, - const u16 port, access_mask_t access_rights); + const u16 port, access_mask_t access_rights, + const u32 flags); #else /* IS_ENABLED(CONFIG_INET) */ static inline void landlock_add_net_hooks(void) { @@ -24,7 +25,7 @@ static inline void landlock_add_net_hooks(void) static inline int landlock_append_net_rule(struct landlock_ruleset *const ruleset, const u16 port, - access_mask_t access_rights) + access_mask_t access_rights, const u32 flags) { return -EAFNOSUPPORT; } diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c index 23779e473563..4dd09ea22c84 100644 --- a/security/landlock/ruleset.c +++ b/security/landlock/ruleset.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "access.h" #include "domain.h" @@ -255,6 +256,7 @@ static int insert_rule(struct landlock_ruleset *const ruleset, if (WARN_ON_ONCE(this->layers[0].level != 0)) return -EINVAL; this->layers[0].access |= (*layers)[0].access; + this->layers[0].flags.quiet |= (*layers)[0].flags.quiet; return 0; } @@ -305,12 +307,15 @@ static void build_check_layer(void) /* @ruleset must be locked by the caller. */ int landlock_insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, - const access_mask_t access) + const access_mask_t access, const u32 flags) { struct landlock_layer layers[] = { { .access = access, /* When @level is zero, insert_rule() extends @ruleset. */ .level = 0, + .flags = { + .quiet = !!(flags & LANDLOCK_ADD_RULE_QUIET), + }, } }; build_check_layer(); @@ -351,6 +356,7 @@ static int merge_tree(struct landlock_ruleset *const dst, return -EINVAL; layers[0].access = walker_rule->layers[0].access; + layers[0].flags = walker_rule->layers[0].flags; err = insert_rule(dst, id, &layers, ARRAY_SIZE(layers)); if (err) @@ -581,6 +587,10 @@ landlock_merge_ruleset(struct landlock_ruleset *const parent, if (err) return ERR_PTR(err); +#ifdef CONFIG_AUDIT + new_dom->hierarchy->quiet_masks = ruleset->quiet_masks; +#endif /* CONFIG_AUDIT */ + return no_free_ptr(new_dom); } diff --git a/security/landlock/ruleset.h b/security/landlock/ruleset.h index ffcb29a1c437..61f3c253d5c9 100644 --- a/security/landlock/ruleset.h +++ b/security/landlock/ruleset.h @@ -156,8 +156,8 @@ struct landlock_ruleset { * @work_free: Enables to free a ruleset within a lockless * section. This is only used by * landlock_put_ruleset_deferred() when @usage reaches zero. - * The fields @lock, @usage, @num_rules, @num_layers and - * @access_masks are then unused. + * The fields @lock, @usage, @num_rules, @num_layers, + * @quiet_masks and @access_masks are then unused. */ struct work_struct work_free; struct { @@ -183,6 +183,12 @@ struct landlock_ruleset { * non-merged ruleset (i.e. not a domain). */ u32 num_layers; + /** + * @quiet_masks: Stores the quiet flags for an unmerged + * ruleset. For a merged domain, this is stored in each + * layer's struct landlock_hierarchy instead. + */ + struct access_masks quiet_masks; /** * @access_masks: Contains the subset of filesystem and * network actions that are restricted by a ruleset. @@ -213,7 +219,7 @@ DEFINE_FREE(landlock_put_ruleset, struct landlock_ruleset *, int landlock_insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, - const access_mask_t access); + const access_mask_t access, const u32 flags); struct landlock_ruleset * landlock_merge_ruleset(struct landlock_ruleset *const parent, diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index d45469d5d464..36b02892c62f 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -105,8 +105,11 @@ static void build_check_abi(void) ruleset_size = sizeof(ruleset_attr.handled_access_fs); ruleset_size += sizeof(ruleset_attr.handled_access_net); ruleset_size += sizeof(ruleset_attr.scoped); + ruleset_size += sizeof(ruleset_attr.quiet_access_fs); + ruleset_size += sizeof(ruleset_attr.quiet_access_net); + ruleset_size += sizeof(ruleset_attr.quiet_scoped); BUILD_BUG_ON(sizeof(ruleset_attr) != ruleset_size); - BUILD_BUG_ON(sizeof(ruleset_attr) != 24); + BUILD_BUG_ON(sizeof(ruleset_attr) != 48); path_beneath_size = sizeof(path_beneath_attr.allowed_access); path_beneath_size += sizeof(path_beneath_attr.parent_fd); @@ -193,6 +196,9 @@ const int landlock_abi_version = 10; * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; * - %EINVAL: unknown @flags, or unknown access, or unknown scope, or too small * @size; + * - %EINVAL: quiet_access_fs, quiet_access_net, or quiet_scoped is not a + * subset of the corresponding handled_access_fs, handled_access_net, or + * scoped; * - %E2BIG: @attr or @size inconsistencies; * - %EFAULT: @attr or @size inconsistencies; * - %ENOMSG: empty &landlock_ruleset_attr.handled_access_fs. @@ -249,6 +255,21 @@ SYSCALL_DEFINE3(landlock_create_ruleset, if ((ruleset_attr.scoped | LANDLOCK_MASK_SCOPE) != LANDLOCK_MASK_SCOPE) return -EINVAL; + /* + * Check that quiet masks are subsets of the respective handled masks. + * Because of the checks above this is sufficient to also ensure that + * the quiet masks are valid access masks. + */ + if ((ruleset_attr.quiet_access_fs | ruleset_attr.handled_access_fs) != + ruleset_attr.handled_access_fs) + return -EINVAL; + if ((ruleset_attr.quiet_access_net | ruleset_attr.handled_access_net) != + ruleset_attr.handled_access_net) + return -EINVAL; + if ((ruleset_attr.quiet_scoped | ruleset_attr.scoped) != + ruleset_attr.scoped) + return -EINVAL; + /* Checks arguments and transforms to kernel struct. */ ruleset = landlock_create_ruleset(ruleset_attr.handled_access_fs, ruleset_attr.handled_access_net, @@ -256,6 +277,10 @@ SYSCALL_DEFINE3(landlock_create_ruleset, if (IS_ERR(ruleset)) return PTR_ERR(ruleset); + ruleset->quiet_masks.fs = ruleset_attr.quiet_access_fs; + ruleset->quiet_masks.net = ruleset_attr.quiet_access_net; + ruleset->quiet_masks.scope = ruleset_attr.quiet_scoped; + /* Creates anonymous FD referring to the ruleset. */ ruleset_fd = anon_inode_getfd("[landlock-ruleset]", &ruleset_fops, ruleset, O_RDWR | O_CLOEXEC); @@ -320,7 +345,7 @@ static int get_path_from_fd(const s32 fd, struct path *const path) } static int add_rule_path_beneath(struct landlock_ruleset *const ruleset, - const void __user *const rule_attr) + const void __user *const rule_attr, u32 flags) { struct landlock_path_beneath_attr path_beneath_attr; struct path path; @@ -335,9 +360,10 @@ static int add_rule_path_beneath(struct landlock_ruleset *const ruleset, /* * Informs about useless rule: empty allowed_access (i.e. deny rules) - * are ignored in path walks. + * are ignored in path walks. However, the rule is not useless if it is + * there to hold a quiet flag. */ - if (!path_beneath_attr.allowed_access) + if (!flags && !path_beneath_attr.allowed_access) return -ENOMSG; /* Checks that allowed_access matches the @ruleset constraints. */ @@ -345,6 +371,10 @@ static int add_rule_path_beneath(struct landlock_ruleset *const ruleset, if ((path_beneath_attr.allowed_access | mask) != mask) return -EINVAL; + /* Checks for useless quiet flag. */ + if (flags & LANDLOCK_ADD_RULE_QUIET && !ruleset->quiet_masks.fs) + return -EINVAL; + /* Gets and checks the new rule. */ err = get_path_from_fd(path_beneath_attr.parent_fd, &path); if (err) @@ -352,13 +382,13 @@ static int add_rule_path_beneath(struct landlock_ruleset *const ruleset, /* Imports the new rule. */ err = landlock_append_fs_rule(ruleset, &path, - path_beneath_attr.allowed_access); + path_beneath_attr.allowed_access, flags); path_put(&path); return err; } static int add_rule_net_port(struct landlock_ruleset *ruleset, - const void __user *const rule_attr) + const void __user *const rule_attr, u32 flags) { struct landlock_net_port_attr net_port_attr; int res; @@ -371,9 +401,10 @@ static int add_rule_net_port(struct landlock_ruleset *ruleset, /* * Informs about useless rule: empty allowed_access (i.e. deny rules) - * are ignored by network actions. + * are ignored by network actions. However, the rule is not useless if + * it is there to hold a quiet flag. */ - if (!net_port_attr.allowed_access) + if (!flags && !net_port_attr.allowed_access) return -ENOMSG; /* Checks that allowed_access matches the @ruleset constraints. */ @@ -381,13 +412,17 @@ static int add_rule_net_port(struct landlock_ruleset *ruleset, if ((net_port_attr.allowed_access | mask) != mask) return -EINVAL; + /* Checks for useless quiet flag. */ + if (flags & LANDLOCK_ADD_RULE_QUIET && !ruleset->quiet_masks.net) + return -EINVAL; + /* Denies inserting a rule with port greater than 65535. */ if (net_port_attr.port > U16_MAX) return -EINVAL; /* Imports the new rule. */ return landlock_append_net_rule(ruleset, net_port_attr.port, - net_port_attr.allowed_access); + net_port_attr.allowed_access, flags); } /** @@ -398,7 +433,7 @@ static int add_rule_net_port(struct landlock_ruleset *ruleset, * @rule_type: Identify the structure type pointed to by @rule_attr: * %LANDLOCK_RULE_PATH_BENEATH or %LANDLOCK_RULE_NET_PORT. * @rule_attr: Pointer to a rule (matching the @rule_type). - * @flags: Must be 0. + * @flags: Must be 0 or %LANDLOCK_ADD_RULE_QUIET. * * This system call enables to define a new rule and add it to an existing * ruleset. @@ -408,20 +443,25 @@ static int add_rule_net_port(struct landlock_ruleset *ruleset, * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; * - %EAFNOSUPPORT: @rule_type is %LANDLOCK_RULE_NET_PORT but TCP/IP is not * supported by the running kernel; - * - %EINVAL: @flags is not 0; + * - %EINVAL: @flags is not valid; * - %EINVAL: The rule accesses are inconsistent (i.e. * &landlock_path_beneath_attr.allowed_access or * &landlock_net_port_attr.allowed_access is not a subset of the ruleset * handled accesses) * - %EINVAL: &landlock_net_port_attr.port is greater than 65535; + * - %EINVAL: LANDLOCK_ADD_RULE_QUIET is passed but the ruleset has no + * quiet access bits set for the corresponding rule type. * - %ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access is - * 0); + * 0) and no flags; * - %EBADF: @ruleset_fd is not a file descriptor for the current thread, or a * member of @rule_attr is not a file descriptor as expected; * - %EBADFD: @ruleset_fd is not a ruleset file descriptor, or a member of * @rule_attr is not the expected file descriptor type; * - %EPERM: @ruleset_fd has no write access to the underlying ruleset; * - %EFAULT: @rule_attr was not a valid address. + * + * .. kernel-doc:: include/uapi/linux/landlock.h + * :identifiers: landlock_add_rule_flags */ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, const enum landlock_rule_type, rule_type, @@ -432,8 +472,7 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, if (!is_initialized()) return -EOPNOTSUPP; - /* No flag for now. */ - if (flags) + if (flags && flags != LANDLOCK_ADD_RULE_QUIET) return -EINVAL; /* Gets and checks the ruleset. */ @@ -443,9 +482,9 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, switch (rule_type) { case LANDLOCK_RULE_PATH_BENEATH: - return add_rule_path_beneath(ruleset, rule_attr); + return add_rule_path_beneath(ruleset, rule_attr, flags); case LANDLOCK_RULE_NET_PORT: - return add_rule_net_port(ruleset, rule_attr); + return add_rule_net_port(ruleset, rule_attr, flags); default: return -EINVAL; } diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c index 6c8113c2ded1..84e91fcaa1b2 100644 --- a/tools/testing/selftests/landlock/base_test.c +++ b/tools/testing/selftests/landlock/base_test.c @@ -201,7 +201,7 @@ TEST(add_rule_checks_ordering) ASSERT_LE(0, ruleset_fd); /* Checks invalid flags. */ - ASSERT_EQ(-1, landlock_add_rule(-1, 0, NULL, 1)); + ASSERT_EQ(-1, landlock_add_rule(-1, 0, NULL, 100)); ASSERT_EQ(EINVAL, errno); /* Checks invalid ruleset FD. */ -- cgit v1.3-14-g43fede From 26330a9226417c9a3395db9fdb403f7d7371e6b7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 11 Jun 2026 13:42:26 +0200 Subject: bpf: Add support to specify uprobe_multi target via file descriptor Allow uprobe_multi link to identify the target binary by an already opened file descriptor. Adding new BPF_F_UPROBE_MULTI_PATH_FD flag and the path_fd field for the attr.link_create.uprobe_multi struct. When the flag is set, we resolve the target from path_fd, without the flag, we keep the existing string path behavior. I don't see a use case for supporting O_PATH file descriptors, because we need to read the binary first to get probes offsets, so I'm using the CLASS(fd, f), which fails for O_PATH fds. Assisted-by: Codex:GPT-5.4 Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20260611114230.950379-4-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 7 ++++++- kernel/bpf/syscall.c | 4 ++-- kernel/trace/bpf_trace.c | 43 ++++++++++++++++++++++++++++++++++++------ tools/include/uapi/linux/bpf.h | 7 ++++++- 4 files changed, 51 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 11dd610fa5fa..89b36de5fdbb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1327,7 +1327,11 @@ enum { * BPF_TRACE_UPROBE_MULTI attach type to create return probe. */ enum { - BPF_F_UPROBE_MULTI_RETURN = (1U << 0) + /* Get return uprobe. */ + BPF_F_UPROBE_MULTI_RETURN = (1U << 0), + + /* Get path from provided path_fd. */ + BPF_F_UPROBE_MULTI_PATH_FD = (1U << 1), }; /* link_create.netfilter.flags used in LINK_CREATE command for @@ -1864,6 +1868,7 @@ union bpf_attr { __u32 cnt; __u32 flags; __u32 pid; + __u32 path_fd; } uprobe_multi; struct { union { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7ed949f70f82..b44106c8ea75 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3480,7 +3480,7 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_KPROBE_MULTI_RETURN ? "kretprobe_multi" : "kprobe_multi"); else if (link->type == BPF_LINK_TYPE_UPROBE_MULTI) - seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_UPROBE_MULTI_RETURN ? + seq_printf(m, "link_type:\t%s\n", link->flags & BPF_F_UPROBE_MULTI_RETURN ? "uretprobe_multi" : "uprobe_multi"); else seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]); @@ -5840,7 +5840,7 @@ err_put: return err; } -#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid +#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.path_fd static int link_create(union bpf_attr *attr, bpfptr_t uattr) { struct bpf_prog *prog; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f8990bc6b64c..82f8feea6931 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -3214,6 +3215,38 @@ static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx) return run_ctx->uprobe->cookie; } +static int bpf_uprobe_multi_get_path(const union bpf_attr *attr, struct path *path) +{ + void __user *upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); + u32 path_fd = attr->link_create.uprobe_multi.path_fd; + u32 flags = attr->link_create.uprobe_multi.flags; + + if (flags & BPF_F_UPROBE_MULTI_PATH_FD) { + /* + * When BPF_F_UPROBE_MULTI_PATH_FD is set, the executable is + * identified by path_fd, upath must be NULL. + */ + if (upath) + return -EINVAL; + + CLASS(fd, f)(path_fd); + if (fd_empty(f)) + return -EBADF; + *path = fd_file(f)->f_path; + path_get(path); + return 0; + } + + /* + * When BPF_F_UPROBE_MULTI_PATH_FD is not set, the path is resolved + * relative to the cwd (AT_FDCWD) or absolute using the upath string. + */ + if (!upath || path_fd) + return -EINVAL; + + return user_path_at(AT_FDCWD, upath, LOOKUP_FOLLOW, path); +} + int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_uprobe_multi_link *link = NULL; @@ -3223,7 +3256,6 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr struct task_struct *task = NULL; unsigned long __user *uoffsets; u64 __user *ucookies; - void __user *upath; unsigned long size; u32 flags, cnt, i; struct path path; @@ -3241,19 +3273,18 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr return -EINVAL; flags = attr->link_create.uprobe_multi.flags; - if (flags & ~BPF_F_UPROBE_MULTI_RETURN) + if (flags & ~(BPF_F_UPROBE_MULTI_RETURN | BPF_F_UPROBE_MULTI_PATH_FD)) return -EINVAL; /* - * path, offsets and cnt are mandatory, + * offsets and cnt are mandatory, * ref_ctr_offsets and cookies are optional */ - upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); cnt = attr->link_create.uprobe_multi.cnt; pid = attr->link_create.uprobe_multi.pid; - if (!upath || !uoffsets || !cnt || pid < 0) + if (!uoffsets || !cnt || pid < 0) return -EINVAL; if (cnt > MAX_UPROBE_MULTI_CNT) return -E2BIG; @@ -3271,7 +3302,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr !access_ok(ucookies, size)) return -EFAULT; - err = user_path_at(AT_FDCWD, upath, LOOKUP_FOLLOW, &path); + err = bpf_uprobe_multi_get_path(attr, &path); if (err) return err; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 11dd610fa5fa..89b36de5fdbb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1327,7 +1327,11 @@ enum { * BPF_TRACE_UPROBE_MULTI attach type to create return probe. */ enum { - BPF_F_UPROBE_MULTI_RETURN = (1U << 0) + /* Get return uprobe. */ + BPF_F_UPROBE_MULTI_RETURN = (1U << 0), + + /* Get path from provided path_fd. */ + BPF_F_UPROBE_MULTI_PATH_FD = (1U << 1), }; /* link_create.netfilter.flags used in LINK_CREATE command for @@ -1864,6 +1868,7 @@ union bpf_attr { __u32 cnt; __u32 flags; __u32 pid; + __u32 path_fd; } uprobe_multi; struct { union { -- cgit v1.3-14-g43fede From 5c4adb7fb46fac348197c5a15c676a066dd1f88e Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Sat, 13 Jun 2026 00:17:03 +0300 Subject: netdev: expose io_uring rx_page_order order via netlink This adds observability for the io_uring zcrx rx-buf-len configuration. Signed-off-by: Dragos Tatulea Reviewed-by: Yael Chemla Reviewed-by: Tariq Toukan Acked-by: Pavel Begunkov Link: https://patch.msgid.link/20260612211709.1456966-3-dtatulea@nvidia.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 9 ++++++++- include/uapi/linux/netdev.h | 2 ++ io_uring/zcrx.c | 8 ++++++++ tools/include/uapi/linux/netdev.h | 2 ++ 4 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 49862b666d7d..5f143da7458c 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -127,7 +127,14 @@ attribute-sets: enum: xsk-flags - name: io-uring-provider-info - attributes: [] + attributes: + - + name: rx-buf-len + type: uint + doc: | + RX buffer length in bytes for this io_uring memory provider. + Reflects the rx_buf_len passed at io_uring zerocopy rx + registration time. - name: page-pool attributes: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 7df1056a35fd..2f3ab75e8cc0 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -97,6 +97,8 @@ enum { }; enum { + NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN = 1, + __NETDEV_A_IO_URING_PROVIDER_INFO_MAX, NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1) }; diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 19837e0b5e91..c7b167c2d4e4 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -1156,6 +1156,7 @@ static void io_pp_zc_destroy(struct page_pool *pp) static int io_pp_nl_fill(void *mp_priv, struct sk_buff *rsp, struct netdev_rx_queue *rxq) { + struct io_zcrx_ifq *ifq = mp_priv; struct nlattr *nest; int type; @@ -1163,6 +1164,13 @@ static int io_pp_nl_fill(void *mp_priv, struct sk_buff *rsp, nest = nla_nest_start(rsp, type); if (!nest) return -EMSGSIZE; + + if (nla_put_uint(rsp, NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN, + 1ULL << ifq->niov_shift)) { + nla_nest_cancel(rsp, nest); + return -EMSGSIZE; + } + nla_nest_end(rsp, nest); return 0; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 7df1056a35fd..2f3ab75e8cc0 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -97,6 +97,8 @@ enum { }; enum { + NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN = 1, + __NETDEV_A_IO_URING_PROVIDER_INFO_MAX, NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1) }; -- cgit v1.3-14-g43fede From 8f9616500c59bb85a06a9d1c52e59d1bf4a194c2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 15 Jun 2026 12:44:16 -0700 Subject: atm: remove orphaned uAPI for deleted drivers, protocols and SVCs ATM removals have left a number of uAPI headers and ioctl definitions with no in-kernel implementation behind them: - device headers for adapters deleted with the legacy PCI/SBUS drivers: atm_eni.h, atm_he.h, atm_idt77105.h, atm_nicstar.h, atm_zatm.h and the atmtcp pair atm_tcp.h / - protocol headers for the removed CLIP, LANE and MPOA stacks: atmarp.h, atmclip.h, atmlec.h, atmmpc.h - atmsvc.h and the SVC / p2mp / local-address ioctls in atmdev.h (ATM_{GET,RST,ADD,DEL}ADDR, ATM_{ADD,DEL,GET}LECSADDR, ATM_{ADD,DROP}PARTY) left behind by the SVC and address-registry removals None of these are referenced by any remaining in-tree code. Let's try to delete all this. Chances are nobody cares about these headers any more. I'm keeping this separate from the kernel side code changes for ease of revert, in case I am proven wrong... Link: https://patch.msgid.link/20260615194416.752559-10-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/atm_tcp.h | 24 ------- include/uapi/linux/atm_eni.h | 24 ------- include/uapi/linux/atm_he.h | 21 ------- include/uapi/linux/atm_idt77105.h | 29 --------- include/uapi/linux/atm_nicstar.h | 54 ---------------- include/uapi/linux/atm_tcp.h | 62 ------------------- include/uapi/linux/atm_zatm.h | 47 -------------- include/uapi/linux/atmarp.h | 42 ------------- include/uapi/linux/atmclip.h | 22 ------- include/uapi/linux/atmdev.h | 18 ------ include/uapi/linux/atmlec.h | 92 --------------------------- include/uapi/linux/atmmpc.h | 127 -------------------------------------- include/uapi/linux/atmsvc.h | 56 ----------------- net/atm/ioctl.c | 1 - 14 files changed, 619 deletions(-) delete mode 100644 include/linux/atm_tcp.h delete mode 100644 include/uapi/linux/atm_eni.h delete mode 100644 include/uapi/linux/atm_he.h delete mode 100644 include/uapi/linux/atm_idt77105.h delete mode 100644 include/uapi/linux/atm_nicstar.h delete mode 100644 include/uapi/linux/atm_tcp.h delete mode 100644 include/uapi/linux/atm_zatm.h delete mode 100644 include/uapi/linux/atmarp.h delete mode 100644 include/uapi/linux/atmclip.h delete mode 100644 include/uapi/linux/atmlec.h delete mode 100644 include/uapi/linux/atmmpc.h delete mode 100644 include/uapi/linux/atmsvc.h (limited to 'include/uapi/linux') diff --git a/include/linux/atm_tcp.h b/include/linux/atm_tcp.h deleted file mode 100644 index 2558439d849b..000000000000 --- a/include/linux/atm_tcp.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* atm_tcp.h - Driver-specific declarations of the ATMTCP driver (for use by - driver-specific utilities) */ - -/* Written 1997-2000 by Werner Almesberger, EPFL LRC/ICA */ - -#ifndef LINUX_ATM_TCP_H -#define LINUX_ATM_TCP_H - -#include - -struct atm_vcc; -struct module; - -struct atm_tcp_ops { - int (*attach)(struct atm_vcc *vcc,int itf); - int (*create_persistent)(int itf); - int (*remove_persistent)(int itf); - struct module *owner; -}; - -extern struct atm_tcp_ops atm_tcp_ops; - -#endif diff --git a/include/uapi/linux/atm_eni.h b/include/uapi/linux/atm_eni.h deleted file mode 100644 index cf5bfd1a2691..000000000000 --- a/include/uapi/linux/atm_eni.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atm_eni.h - Driver-specific declarations of the ENI driver (for use by - driver-specific utilities) */ - -/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ - - -#ifndef LINUX_ATM_ENI_H -#define LINUX_ATM_ENI_H - -#include - - -struct eni_multipliers { - int tx,rx; /* values are in percent and must be > 100 */ -}; - - -#define ENI_MEMDUMP _IOW('a',ATMIOC_SARPRV,struct atmif_sioc) - /* printk memory map */ -#define ENI_SETMULT _IOW('a',ATMIOC_SARPRV+7,struct atmif_sioc) - /* set buffer multipliers */ - -#endif diff --git a/include/uapi/linux/atm_he.h b/include/uapi/linux/atm_he.h deleted file mode 100644 index 9f4b43293988..000000000000 --- a/include/uapi/linux/atm_he.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atm_he.h */ - -#ifndef LINUX_ATM_HE_H -#define LINUX_ATM_HE_H - -#include - -#define HE_GET_REG _IOW('a', ATMIOC_SARPRV, struct atmif_sioc) - -#define HE_REGTYPE_PCI 1 -#define HE_REGTYPE_RCM 2 -#define HE_REGTYPE_TCM 3 -#define HE_REGTYPE_MBOX 4 - -struct he_ioctl_reg { - unsigned addr, val; - char type; -}; - -#endif /* LINUX_ATM_HE_H */ diff --git a/include/uapi/linux/atm_idt77105.h b/include/uapi/linux/atm_idt77105.h deleted file mode 100644 index f0fd6912a14b..000000000000 --- a/include/uapi/linux/atm_idt77105.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atm_idt77105.h - Driver-specific declarations of the IDT77105 driver (for - * use by driver-specific utilities) */ - -/* Written 1999 by Greg Banks . Copied from atm_suni.h. */ - - -#ifndef LINUX_ATM_IDT77105_H -#define LINUX_ATM_IDT77105_H - -#include -#include -#include - -/* - * Structure for IDT77105_GETSTAT and IDT77105_GETSTATZ ioctls. - * Pointed to by `arg' in atmif_sioc. - */ -struct idt77105_stats { - __u32 symbol_errors; /* wire symbol errors */ - __u32 tx_cells; /* cells transmitted */ - __u32 rx_cells; /* cells received */ - __u32 rx_hec_errors; /* Header Error Check errors on receive */ -}; - -#define IDT77105_GETSTAT _IOW('a',ATMIOC_PHYPRV+2,struct atmif_sioc) /* get stats */ -#define IDT77105_GETSTATZ _IOW('a',ATMIOC_PHYPRV+3,struct atmif_sioc) /* get stats and zero */ - -#endif diff --git a/include/uapi/linux/atm_nicstar.h b/include/uapi/linux/atm_nicstar.h deleted file mode 100644 index 880d368b5b9a..000000000000 --- a/include/uapi/linux/atm_nicstar.h +++ /dev/null @@ -1,54 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/****************************************************************************** - * - * atm_nicstar.h - * - * Driver-specific declarations for use by NICSTAR driver specific utils. - * - * Author: Rui Prior - * - * (C) INESC 1998 - * - ******************************************************************************/ - - -#ifndef LINUX_ATM_NICSTAR_H -#define LINUX_ATM_NICSTAR_H - -/* Note: non-kernel programs including this file must also include - * sys/types.h for struct timeval - */ - -#include -#include - -#define NS_GETPSTAT _IOWR('a',ATMIOC_SARPRV+1,struct atmif_sioc) - /* get pool statistics */ -#define NS_SETBUFLEV _IOW('a',ATMIOC_SARPRV+2,struct atmif_sioc) - /* set buffer level markers */ -#define NS_ADJBUFLEV _IO('a',ATMIOC_SARPRV+3) - /* adjust buffer level */ - -typedef struct buf_nr -{ - unsigned min; - unsigned init; - unsigned max; -}buf_nr; - - -typedef struct pool_levels -{ - int buftype; - int count; /* (At least for now) only used in NS_GETPSTAT */ - buf_nr level; -} pool_levels; - -/* type must be one of the following: */ -#define NS_BUFTYPE_SMALL 1 -#define NS_BUFTYPE_LARGE 2 -#define NS_BUFTYPE_HUGE 3 -#define NS_BUFTYPE_IOVEC 4 - - -#endif /* LINUX_ATM_NICSTAR_H */ diff --git a/include/uapi/linux/atm_tcp.h b/include/uapi/linux/atm_tcp.h deleted file mode 100644 index 7309e1bc8867..000000000000 --- a/include/uapi/linux/atm_tcp.h +++ /dev/null @@ -1,62 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atm_tcp.h - Driver-specific declarations of the ATMTCP driver (for use by - driver-specific utilities) */ - -/* Written 1997-2000 by Werner Almesberger, EPFL LRC/ICA */ - - -#ifndef _UAPILINUX_ATM_TCP_H -#define _UAPILINUX_ATM_TCP_H - -#include -#include -#include -#include - - -/* - * All values in struct atmtcp_hdr are in network byte order - */ - -struct atmtcp_hdr { - __u16 vpi; - __u16 vci; - __u32 length; /* ... of data part */ -}; - -/* - * All values in struct atmtcp_command are in host byte order - */ - -#define ATMTCP_HDR_MAGIC (~0) /* this length indicates a command */ -#define ATMTCP_CTRL_OPEN 1 /* request/reply */ -#define ATMTCP_CTRL_CLOSE 2 /* request/reply */ - -struct atmtcp_control { - struct atmtcp_hdr hdr; /* must be first */ - int type; /* message type; both directions */ - atm_kptr_t vcc; /* both directions */ - struct sockaddr_atmpvc addr; /* suggested value from kernel */ - struct atm_qos qos; /* both directions */ - int result; /* to kernel only */ -} __ATM_API_ALIGN; - -/* - * Field usage: - * Messge type dir. hdr.v?i type addr qos vcc result - * ----------- ---- ------- ---- ---- --- --- ------ - * OPEN K->D Y Y Y Y Y 0 - * OPEN D->K - Y Y Y Y Y - * CLOSE K->D - - Y - Y 0 - * CLOSE D->K - - - - Y Y - */ - -#define SIOCSIFATMTCP _IO('a',ATMIOC_ITF) /* set ATMTCP mode */ -#define ATMTCP_CREATE _IO('a',ATMIOC_ITF+14) /* create persistent ATMTCP - interface */ -#define ATMTCP_REMOVE _IO('a',ATMIOC_ITF+15) /* destroy persistent ATMTCP - interface */ - - - -#endif /* _UAPILINUX_ATM_TCP_H */ diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h deleted file mode 100644 index 5135027b93c1..000000000000 --- a/include/uapi/linux/atm_zatm.h +++ /dev/null @@ -1,47 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atm_zatm.h - Driver-specific declarations of the ZATM driver (for use by - driver-specific utilities) */ - -/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */ - - -#ifndef LINUX_ATM_ZATM_H -#define LINUX_ATM_ZATM_H - -/* - * Note: non-kernel programs including this file must also include - * sys/types.h for struct timeval - */ - -#include -#include - -#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) - /* get pool statistics */ -#define ZATM_GETPOOLZ _IOW('a',ATMIOC_SARPRV+2,struct atmif_sioc) - /* get statistics and zero */ -#define ZATM_SETPOOL _IOW('a',ATMIOC_SARPRV+3,struct atmif_sioc) - /* set pool parameters */ - -struct zatm_pool_info { - int ref_count; /* free buffer pool usage counters */ - int low_water,high_water; /* refill parameters */ - int rqa_count,rqu_count; /* queue condition counters */ - int offset,next_off; /* alignment optimizations: offset */ - int next_cnt,next_thres; /* repetition counter and threshold */ -}; - -struct zatm_pool_req { - int pool_num; /* pool number */ - struct zatm_pool_info info; /* actual information */ -}; - -#define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */ -#define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */ -#define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */ -#define ZATM_LAST_POOL ZATM_AAL5_POOL_BASE+10 /* max. 64 kB */ - -#define ZATM_TIMER_HISTORY_SIZE 16 /* number of timer adjustments to - record; must be 2^n */ - -#endif diff --git a/include/uapi/linux/atmarp.h b/include/uapi/linux/atmarp.h deleted file mode 100644 index 8e44d121fde1..000000000000 --- a/include/uapi/linux/atmarp.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atmarp.h - ATM ARP protocol and kernel-demon interface definitions */ - -/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */ - - -#ifndef _LINUX_ATMARP_H -#define _LINUX_ATMARP_H - -#include -#include -#include - - -#define ATMARP_RETRY_DELAY 30 /* request next resolution or forget - NAK after 30 sec - should go into - atmclip.h */ -#define ATMARP_MAX_UNRES_PACKETS 5 /* queue that many packets while - waiting for the resolver */ - - -#define ATMARPD_CTRL _IO('a',ATMIOC_CLIP+1) /* become atmarpd ctrl sock */ -#define ATMARP_MKIP _IO('a',ATMIOC_CLIP+2) /* attach socket to IP */ -#define ATMARP_SETENTRY _IO('a',ATMIOC_CLIP+3) /* fill or hide ARP entry */ -#define ATMARP_ENCAP _IO('a',ATMIOC_CLIP+5) /* change encapsulation */ - - -enum atmarp_ctrl_type { - act_invalid, /* catch uninitialized structures */ - act_need, /* need address resolution */ - act_up, /* interface is coming up */ - act_down, /* interface is going down */ - act_change /* interface configuration has changed */ -}; - -struct atmarp_ctrl { - enum atmarp_ctrl_type type; /* message type */ - int itf_num;/* interface number (if present) */ - __be32 ip; /* IP address (act_need only) */ -}; - -#endif diff --git a/include/uapi/linux/atmclip.h b/include/uapi/linux/atmclip.h deleted file mode 100644 index c818bb82b4e6..000000000000 --- a/include/uapi/linux/atmclip.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atmclip.h - Classical IP over ATM */ - -/* Written 1995-1998 by Werner Almesberger, EPFL LRC/ICA */ - - -#ifndef LINUX_ATMCLIP_H -#define LINUX_ATMCLIP_H - -#include -#include - - -#define RFC1483LLC_LEN 8 /* LLC+OUI+PID = 8 */ -#define RFC1626_MTU 9180 /* RFC1626 default MTU */ - -#define CLIP_DEFAULT_IDLETIMER 1200 /* 20 minutes, see RFC1755 */ -#define CLIP_CHECK_INTERVAL 10 /* check every ten seconds */ - -#define SIOCMKCLIP _IO('a',ATMIOC_CLIP) /* create IP interface */ - -#endif diff --git a/include/uapi/linux/atmdev.h b/include/uapi/linux/atmdev.h index 20b0215084fc..a94e7b8360ee 100644 --- a/include/uapi/linux/atmdev.h +++ b/include/uapi/linux/atmdev.h @@ -60,14 +60,6 @@ struct atm_dev_stats { /* get interface type name */ #define ATM_GETESI _IOW('a',ATMIOC_ITF+5,struct atmif_sioc) /* get interface ESI */ -#define ATM_GETADDR _IOW('a',ATMIOC_ITF+6,struct atmif_sioc) - /* get itf's local ATM addr. list */ -#define ATM_RSTADDR _IOW('a',ATMIOC_ITF+7,struct atmif_sioc) - /* reset itf's ATM address list */ -#define ATM_ADDADDR _IOW('a',ATMIOC_ITF+8,struct atmif_sioc) - /* add a local ATM address */ -#define ATM_DELADDR _IOW('a',ATMIOC_ITF+9,struct atmif_sioc) - /* remove a local ATM address */ #define ATM_GETCIRANGE _IOW('a',ATMIOC_ITF+10,struct atmif_sioc) /* get connection identifier range */ #define ATM_SETCIRANGE _IOW('a',ATMIOC_ITF+11,struct atmif_sioc) @@ -76,12 +68,6 @@ struct atm_dev_stats { /* set interface ESI */ #define ATM_SETESIF _IOW('a',ATMIOC_ITF+13,struct atmif_sioc) /* force interface ESI */ -#define ATM_ADDLECSADDR _IOW('a', ATMIOC_ITF+14, struct atmif_sioc) - /* register a LECS address */ -#define ATM_DELLECSADDR _IOW('a', ATMIOC_ITF+15, struct atmif_sioc) - /* unregister a LECS address */ -#define ATM_GETLECSADDR _IOW('a', ATMIOC_ITF+16, struct atmif_sioc) - /* retrieve LECS address(es) */ #define ATM_GETSTAT _IOW('a',ATMIOC_SARCOM+0,struct atmif_sioc) /* get AAL layer statistics */ @@ -99,10 +85,6 @@ struct atm_dev_stats { /* set backend handler */ #define ATM_NEWBACKENDIF _IOW('a',ATMIOC_SPECIAL+3,atm_backend_t) /* use backend to make new if */ -#define ATM_ADDPARTY _IOW('a', ATMIOC_SPECIAL+4,struct atm_iobuf) - /* add party to p2mp call */ -#define ATM_DROPPARTY _IOW('a', ATMIOC_SPECIAL+5,int) - /* drop party from p2mp call */ /* * These are backend handkers that can be set via the ATM_SETBACKEND call diff --git a/include/uapi/linux/atmlec.h b/include/uapi/linux/atmlec.h deleted file mode 100644 index c68346bb40e6..000000000000 --- a/include/uapi/linux/atmlec.h +++ /dev/null @@ -1,92 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * ATM Lan Emulation Daemon driver interface - * - * Marko Kiiskila - */ - -#ifndef _ATMLEC_H_ -#define _ATMLEC_H_ - -#include -#include -#include -#include -#include - -/* ATM lec daemon control socket */ -#define ATMLEC_CTRL _IO('a', ATMIOC_LANE) -#define ATMLEC_DATA _IO('a', ATMIOC_LANE+1) -#define ATMLEC_MCAST _IO('a', ATMIOC_LANE+2) - -/* Maximum number of LEC interfaces (tweakable) */ -#define MAX_LEC_ITF 48 - -typedef enum { - l_set_mac_addr, - l_del_mac_addr, - l_svc_setup, - l_addr_delete, - l_topology_change, - l_flush_complete, - l_arp_update, - l_narp_req, /* LANE2 mandates the use of this */ - l_config, - l_flush_tran_id, - l_set_lecid, - l_arp_xmt, - l_rdesc_arp_xmt, - l_associate_req, - l_should_bridge /* should we bridge this MAC? */ -} atmlec_msg_type; - -#define ATMLEC_MSG_TYPE_MAX l_should_bridge - -struct atmlec_config_msg { - unsigned int maximum_unknown_frame_count; - unsigned int max_unknown_frame_time; - unsigned short max_retry_count; - unsigned int aging_time; - unsigned int forward_delay_time; - unsigned int arp_response_time; - unsigned int flush_timeout; - unsigned int path_switching_delay; - unsigned int lane_version; /* LANE2: 1 for LANEv1, 2 for LANEv2 */ - int mtu; - int is_proxy; -}; - -struct atmlec_msg { - atmlec_msg_type type; - int sizeoftlvs; /* LANE2: if != 0, tlvs follow */ - union { - struct { - unsigned char mac_addr[ETH_ALEN]; - unsigned char atm_addr[ATM_ESA_LEN]; - unsigned int flag; /* - * Topology_change flag, - * remoteflag, permanent flag, - * lecid, transaction id - */ - unsigned int targetless_le_arp; /* LANE2 */ - unsigned int no_source_le_narp; /* LANE2 */ - } normal; - struct atmlec_config_msg config; - struct { - __u16 lec_id; /* requestor lec_id */ - __u32 tran_id; /* transaction id */ - unsigned char mac_addr[ETH_ALEN]; /* dst mac addr */ - unsigned char atm_addr[ATM_ESA_LEN]; /* reqestor ATM addr */ - } proxy; /* - * For mapping LE_ARP requests to responses. Filled by - * zeppelin, returned by kernel. Used only when proxying - */ - } content; -} __ATM_API_ALIGN; - -struct atmlec_ioc { - int dev_num; - unsigned char atm_addr[ATM_ESA_LEN]; - unsigned char receive; /* 1= receive vcc, 0 = send vcc */ -}; -#endif /* _ATMLEC_H_ */ diff --git a/include/uapi/linux/atmmpc.h b/include/uapi/linux/atmmpc.h deleted file mode 100644 index cc17f4304839..000000000000 --- a/include/uapi/linux/atmmpc.h +++ /dev/null @@ -1,127 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _ATMMPC_H_ -#define _ATMMPC_H_ - -#include -#include -#include -#include - -#define ATMMPC_CTRL _IO('a', ATMIOC_MPOA) -#define ATMMPC_DATA _IO('a', ATMIOC_MPOA+1) - -#define MPC_SOCKET_INGRESS 1 -#define MPC_SOCKET_EGRESS 2 - -struct atmmpc_ioc { - int dev_num; - __be32 ipaddr; /* the IP address of the shortcut */ - int type; /* ingress or egress */ -}; - -typedef struct in_ctrl_info { - __u8 Last_NHRP_CIE_code; - __u8 Last_Q2931_cause_value; - __u8 eg_MPC_ATM_addr[ATM_ESA_LEN]; - __be32 tag; - __be32 in_dst_ip; /* IP address this ingress MPC sends packets to */ - __u16 holding_time; - __u32 request_id; -} in_ctrl_info; - -typedef struct eg_ctrl_info { - __u8 DLL_header[256]; - __u8 DH_length; - __be32 cache_id; - __be32 tag; - __be32 mps_ip; - __be32 eg_dst_ip; /* IP address to which ingress MPC sends packets */ - __u8 in_MPC_data_ATM_addr[ATM_ESA_LEN]; - __u16 holding_time; -} eg_ctrl_info; - -struct mpc_parameters { - __u16 mpc_p1; /* Shortcut-Setup Frame Count */ - __u16 mpc_p2; /* Shortcut-Setup Frame Time */ - __u8 mpc_p3[8]; /* Flow-detection Protocols */ - __u16 mpc_p4; /* MPC Initial Retry Time */ - __u16 mpc_p5; /* MPC Retry Time Maximum */ - __u16 mpc_p6; /* Hold Down Time */ -} ; - -struct k_message { - __u16 type; - __be32 ip_mask; - __u8 MPS_ctrl[ATM_ESA_LEN]; - union { - in_ctrl_info in_info; - eg_ctrl_info eg_info; - struct mpc_parameters params; - } content; - struct atm_qos qos; -} __ATM_API_ALIGN; - -struct llc_snap_hdr { - /* RFC 1483 LLC/SNAP encapsulation for routed IP PDUs */ - __u8 dsap; /* Destination Service Access Point (0xAA) */ - __u8 ssap; /* Source Service Access Point (0xAA) */ - __u8 ui; /* Unnumbered Information (0x03) */ - __u8 org[3]; /* Organizational identification (0x000000) */ - __u8 type[2]; /* Ether type (for IP) (0x0800) */ -}; - -/* TLVs this MPC recognizes */ -#define TLV_MPOA_DEVICE_TYPE 0x00a03e2a - -/* MPOA device types in MPOA Device Type TLV */ -#define NON_MPOA 0 -#define MPS 1 -#define MPC 2 -#define MPS_AND_MPC 3 - - -/* MPC parameter defaults */ - -#define MPC_P1 10 /* Shortcut-Setup Frame Count */ -#define MPC_P2 1 /* Shortcut-Setup Frame Time */ -#define MPC_P3 0 /* Flow-detection Protocols */ -#define MPC_P4 5 /* MPC Initial Retry Time */ -#define MPC_P5 40 /* MPC Retry Time Maximum */ -#define MPC_P6 160 /* Hold Down Time */ -#define HOLDING_TIME_DEFAULT 1200 /* same as MPS-p7 */ - -/* MPC constants */ - -#define MPC_C1 2 /* Retry Time Multiplier */ -#define MPC_C2 60 /* Initial Keep-Alive Lifetime */ - -/* Message types - to MPOA daemon */ - -#define SND_MPOA_RES_RQST 201 -#define SET_MPS_CTRL_ADDR 202 -#define SND_MPOA_RES_RTRY 203 /* Different type in a retry due to req id */ -#define STOP_KEEP_ALIVE_SM 204 -#define EGRESS_ENTRY_REMOVED 205 -#define SND_EGRESS_PURGE 206 -#define DIE 207 /* tell the daemon to exit() */ -#define DATA_PLANE_PURGE 208 /* Data plane purge because of egress cache hit miss or dead MPS */ -#define OPEN_INGRESS_SVC 209 - -/* Message types - from MPOA daemon */ - -#define MPOA_TRIGGER_RCVD 101 -#define MPOA_RES_REPLY_RCVD 102 -#define INGRESS_PURGE_RCVD 103 -#define EGRESS_PURGE_RCVD 104 -#define MPS_DEATH 105 -#define CACHE_IMPOS_RCVD 106 -#define SET_MPC_CTRL_ADDR 107 /* Our MPC's control ATM address */ -#define SET_MPS_MAC_ADDR 108 -#define CLEAN_UP_AND_EXIT 109 -#define SET_MPC_PARAMS 110 /* MPC configuration parameters */ - -/* Message types - bidirectional */ - -#define RELOAD 301 /* kill -HUP the daemon for reload */ - -#endif /* _ATMMPC_H_ */ diff --git a/include/uapi/linux/atmsvc.h b/include/uapi/linux/atmsvc.h deleted file mode 100644 index 137b5f853449..000000000000 --- a/include/uapi/linux/atmsvc.h +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atmsvc.h - ATM signaling kernel-demon interface definitions */ - -/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ - - -#ifndef _LINUX_ATMSVC_H -#define _LINUX_ATMSVC_H - -#include -#include -#include - - -#define ATMSIGD_CTRL _IO('a',ATMIOC_SPECIAL) - /* become ATM signaling demon control socket */ - -enum atmsvc_msg_type { as_catch_null, as_bind, as_connect, as_accept, as_reject, - as_listen, as_okay, as_error, as_indicate, as_close, - as_itf_notify, as_modify, as_identify, as_terminate, - as_addparty, as_dropparty }; - -struct atmsvc_msg { - enum atmsvc_msg_type type; - atm_kptr_t vcc; - atm_kptr_t listen_vcc; /* indicate */ - int reply; /* for okay and close: */ - /* < 0: error before active */ - /* (sigd has discarded ctx) */ - /* ==0: success */ - /* > 0: error when active (still */ - /* need to close) */ - struct sockaddr_atmpvc pvc; /* indicate, okay (connect) */ - struct sockaddr_atmsvc local; /* local SVC address */ - struct atm_qos qos; /* QOS parameters */ - struct atm_sap sap; /* SAP */ - unsigned int session; /* for p2pm */ - struct sockaddr_atmsvc svc; /* SVC address */ -} __ATM_API_ALIGN; - -/* - * Message contents: see ftp://icaftp.epfl.ch/pub/linux/atm/docs/isp-*.tar.gz - */ - -/* - * Some policy stuff for atmsigd and for net/atm/svc.c. Both have to agree on - * what PCR is used to request bandwidth from the device driver. net/atm/svc.c - * tries to do better than that, but only if there's no routing decision (i.e. - * if signaling only uses one ATM interface). - */ - -#define SELECT_TOP_PCR(tp) ((tp).pcr ? (tp).pcr : \ - (tp).max_pcr && (tp).max_pcr != ATM_MAX_PCR ? (tp).max_pcr : \ - (tp).min_pcr ? (tp).min_pcr : ATM_MAX_PCR) - -#endif diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 11f6d236f5d6..194587fc15e8 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -11,7 +11,6 @@ #include /* struct socket, struct proto_ops */ #include /* ATM stuff */ #include -#include /* manifest constants */ #include #include #include -- cgit v1.3-14-g43fede From b8b09dc2bf35a00d4e0556b5d6308c7b917ebda2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 18 Jun 2026 13:56:38 +0200 Subject: netfilter: nf_conntrack_expect: use conntrack GC to reap expectations This patch replaces the timer API by GC worker approach for expectations, as it already happened in many other subsystems. Use the existing conntrack GC worker to iterate over the local list of expectations in the master conntrack to reap expired expectations. Check IPS_HELPER_BIT to run GC for expectations, set it on for nft_ct expectation which nevers sets it. Hold the expectation spinlock while iterating over the master conntrack expectation list to synchronize with nf_ct_remove_expectations(). This also performs runtime packet path garbage collection through the expectation insertion and lookup functions while walking over one of the chains of the global expectation hashtables. Unconfirmed conntrack entries are skipped since ct->ext can be reallocated and dying are skipped since those will be gone soon. Set on IPS_HELPER_BIT if the helper ct extension is added, then the new GC worker does not need to bump the ct refcount to check if the ct->ext helper is available. This removes the extra bump on the refcount for expectation timers, this allows to remove several nf_ct_expect_put() calls after the unlink, after this update only refcount remains at 1 while on the expectation hashes. This patch implicitly addresses a race with the existing timer API allowing an expectation to access a stale exp->master pointer which has been already released when expectation removal loses races with an expiring timer, ie. timer_del() reporting false. Add a new NF_CT_EXPECT_DEAD flag to reap this expectation via GC. This is needed by nf_conntrack_unexpect_related() which is called in error paths to invalidate newly created expectations that has been added into the hashes. These expectactions cannot be inmediately released as GC or nf_ct_remove_expectations() could race to make it. On expectation insert, the runtime GC reaps stale expectations before checking the expectation limit set by policy. Set current timestamp in nf_ct_expect_alloc(), then add the expectation policy timeout (or custom timeout specified added on top of this) to specify the expectation lifetime. Fixes: bffcaad9afdf ("netfilter: ctnetlink: ensure safe access to master conntrack") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_expect.h | 16 ++- include/uapi/linux/netfilter/nf_conntrack_common.h | 1 + net/netfilter/nf_conntrack_core.c | 33 ++++- net/netfilter/nf_conntrack_expect.c | 145 ++++++++++----------- net/netfilter/nf_conntrack_h323_main.c | 4 +- net/netfilter/nf_conntrack_helper.c | 10 +- net/netfilter/nf_conntrack_netlink.c | 22 ++-- net/netfilter/nf_conntrack_sip.c | 13 +- net/netfilter/nft_ct.c | 3 +- 9 files changed, 139 insertions(+), 108 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 80f50fd0f7ad..be4a120d549e 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -54,8 +54,8 @@ struct nf_conntrack_expect { /* The conntrack of the master connection */ struct nf_conn *master; - /* Timer function; deletes the expectation. */ - struct timer_list timeout; + /* jiffies32 when this expectation expires */ + u32 timeout; #if IS_ENABLED(CONFIG_NF_NAT) union nf_inet_addr saved_addr; @@ -69,6 +69,14 @@ struct nf_conntrack_expect { struct rcu_head rcu; }; +static inline bool nf_ct_exp_is_expired(const struct nf_conntrack_expect *exp) +{ + if (READ_ONCE(exp->flags) & NF_CT_EXPECT_DEAD) + return true; + + return (__s32)(READ_ONCE(exp->timeout) - nfct_time_stamp) <= 0; +} + static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) { return read_pnet(&exp->net); @@ -130,7 +138,6 @@ static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) void nf_ct_remove_expectations(struct nf_conn *ct); void nf_ct_unexpect_related(struct nf_conntrack_expect *exp); -bool nf_ct_remove_expect(struct nf_conntrack_expect *exp); void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, void *data), void *data); void nf_ct_expect_iterate_net(struct net *net, @@ -153,5 +160,8 @@ static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect, return nf_ct_expect_related_report(expect, 0, 0, flags); } +struct nf_conn_help; +void nf_ct_expectation_gc(struct nf_conn_help *master_help); + #endif /*_NF_CONNTRACK_EXPECT_H*/ diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 56b6b60a814f..ee51045ae1d6 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -160,6 +160,7 @@ enum ip_conntrack_expect_events { #define NF_CT_EXPECT_USERSPACE 0x4 #ifdef __KERNEL__ +#define NF_CT_EXPECT_DEAD 0x8 #define NF_CT_EXPECT_MASK (NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE | \ NF_CT_EXPECT_USERSPACE) #endif diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 4fb3a2d18631..784bd1d7a9bf 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1471,6 +1471,31 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) return false; } +static void nf_ct_help_gc(struct nf_conn *ct) +{ + struct nf_conn_help *help; + + if (!refcount_inc_not_zero(&ct->ct_general.use)) + return; + + /* load ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + + if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct)) { + nf_ct_put(ct); + return; + } + + /* re-check helper due to SLAB_TYPESAFE_BY_RCU */ + if (test_bit(IPS_HELPER_BIT, &ct->status)) { + help = nfct_help(ct); + if (help) + nf_ct_expectation_gc(help); + } + + nf_ct_put(ct); +} + static void gc_worker(struct work_struct *work) { unsigned int i, hashsz, nf_conntrack_max95 = 0; @@ -1543,7 +1568,13 @@ static void gc_worker(struct work_struct *work) expires = (expires - (long)next_run) / ++count; next_run += expires; - if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp)) + if (gc_worker_skip_ct(tmp)) + continue; + + if (test_bit(IPS_HELPER_BIT, &tmp->status)) + nf_ct_help_gc(tmp); + + if (nf_conntrack_max95 == 0) continue; net = nf_ct_net(tmp); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 5c9b17835c28..49e18eda037e 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -43,6 +43,24 @@ unsigned int nf_ct_expect_max __read_mostly; static struct kmem_cache *nf_ct_expect_cachep __read_mostly; static siphash_aligned_key_t nf_ct_expect_hashrnd; +void nf_ct_expectation_gc(struct nf_conn_help *master_help) +{ + struct nf_conntrack_expect *exp; + struct hlist_node *next; + + if (hlist_empty(&master_help->expectations)) + return; + + spin_lock_bh(&nf_conntrack_expect_lock); + hlist_for_each_entry_safe(exp, next, &master_help->expectations, lnode) { + if (!nf_ct_exp_is_expired(exp)) + continue; + + nf_ct_unlink_expect(exp); + } + spin_unlock_bh(&nf_conntrack_expect_lock); +} + /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, u32 portid, int report) @@ -52,7 +70,6 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, struct nf_conntrack_net *cnet; lockdep_nfct_expect_lock_held(); - WARN_ON_ONCE(timer_pending(&exp->timeout)); hlist_del_rcu(&exp->hnode); @@ -70,16 +87,6 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, } EXPORT_SYMBOL_GPL(nf_ct_unlink_expect_report); -static void nf_ct_expectation_timed_out(struct timer_list *t) -{ - struct nf_conntrack_expect *exp = timer_container_of(exp, t, timeout); - - spin_lock_bh(&nf_conntrack_expect_lock); - nf_ct_unlink_expect(exp); - spin_unlock_bh(&nf_conntrack_expect_lock); - nf_ct_expect_put(exp); -} - static unsigned int nf_ct_expect_dst_hash(const struct net *n, const struct nf_conntrack_tuple *tuple) { struct { @@ -117,19 +124,6 @@ nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple, nf_ct_exp_zone_equal_any(i, zone); } -bool nf_ct_remove_expect(struct nf_conntrack_expect *exp) -{ - lockdep_nfct_expect_lock_held(); - - if (timer_delete(&exp->timeout)) { - nf_ct_unlink_expect(exp); - nf_ct_expect_put(exp); - return true; - } - return false; -} -EXPORT_SYMBOL_GPL(nf_ct_remove_expect); - struct nf_conntrack_expect * __nf_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, @@ -144,6 +138,8 @@ __nf_ct_expect_find(struct net *net, h = nf_ct_expect_dst_hash(net, tuple); hlist_for_each_entry_rcu(i, &nf_ct_expect_hash[h], hnode) { + if (nf_ct_exp_is_expired(i)) + continue; if (nf_ct_exp_equal(tuple, i, zone, net)) return i; } @@ -178,6 +174,7 @@ nf_ct_find_expectation(struct net *net, { struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_conntrack_expect *i, *exp = NULL; + struct hlist_node *next; unsigned int h; lockdep_nfct_expect_lock_held(); @@ -186,7 +183,11 @@ nf_ct_find_expectation(struct net *net, return NULL; h = nf_ct_expect_dst_hash(net, tuple); - hlist_for_each_entry(i, &nf_ct_expect_hash[h], hnode) { + hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { + if (nf_ct_exp_is_expired(i)) { + nf_ct_unlink_expect(i); + continue; + } if (!(i->flags & NF_CT_EXPECT_INACTIVE) && nf_ct_exp_equal(tuple, i, zone, net)) { exp = i; @@ -196,13 +197,16 @@ nf_ct_find_expectation(struct net *net, if (!exp) return NULL; + if (!refcount_inc_not_zero(&exp->use)) + return NULL; + /* If master is not in hash table yet (ie. packet hasn't left this machine yet), how can other end know about expected? Hence these are not the droids you are looking for (if master ct never got confirmed, we'd hold a reference to it and weird things would happen to future packets). */ if (!nf_ct_is_confirmed(exp->master)) - return NULL; + goto err_release_exp; /* Avoid race with other CPUs, that for exp->master ct, is * about to invoke ->destroy(), or nf_ct_delete() via timeout @@ -214,18 +218,17 @@ nf_ct_find_expectation(struct net *net, */ if (unlikely(nf_ct_is_dying(exp->master) || !refcount_inc_not_zero(&exp->master->ct_general.use))) - return NULL; + goto err_release_exp; - if (exp->flags & NF_CT_EXPECT_PERMANENT || !unlink) { - refcount_inc(&exp->use); - return exp; - } else if (timer_delete(&exp->timeout)) { - nf_ct_unlink_expect(exp); + if (exp->flags & NF_CT_EXPECT_PERMANENT || !unlink) return exp; - } - /* Undo exp->master refcnt increase, if timer_delete() failed */ - nf_ct_put(exp->master); + nf_ct_unlink_expect(exp); + + return exp; + +err_release_exp: + nf_ct_expect_put(exp); return NULL; } @@ -241,9 +244,8 @@ void nf_ct_remove_expectations(struct nf_conn *ct) return; spin_lock_bh(&nf_conntrack_expect_lock); - hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { - nf_ct_remove_expect(exp); - } + hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) + nf_ct_unlink_expect(exp); spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_remove_expectations); @@ -292,7 +294,7 @@ static bool master_matches(const struct nf_conntrack_expect *a, void nf_ct_unexpect_related(struct nf_conntrack_expect *exp) { spin_lock_bh(&nf_conntrack_expect_lock); - nf_ct_remove_expect(exp); + WRITE_ONCE(exp->flags, exp->flags | NF_CT_EXPECT_DEAD); spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_unexpect_related); @@ -308,6 +310,7 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me) if (!new) return NULL; + new->timeout = nfct_time_stamp; new->master = me; refcount_set(&new->use, 1); return new; @@ -413,17 +416,12 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp, struct net *net = nf_ct_exp_net(exp); unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple); - /* two references : one for hash insert, one for the timer */ - refcount_add(2, &exp->use); + refcount_inc(&exp->use); - timer_setup(&exp->timeout, nf_ct_expectation_timed_out, 0); helper = rcu_dereference_protected(master_help->helper, lockdep_is_held(&nf_conntrack_expect_lock)); - if (helper) { - exp->timeout.expires = jiffies + - helper->expect_policy[exp->class].timeout * HZ; - } - add_timer(&exp->timeout); + if (helper) + exp->timeout += helper->expect_policy[exp->class].timeout * HZ; hlist_add_head_rcu(&exp->lnode, &master_help->expectations); master_help->expecting[exp->class]++; @@ -435,19 +433,26 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp, NF_CT_STAT_INC(net, expect_create); } -/* Race with expectations being used means we could have none to find; OK. */ static void evict_oldest_expect(struct nf_conn_help *master_help, - struct nf_conntrack_expect *new) + struct nf_conntrack_expect *new, + const struct nf_conntrack_expect_policy *p) { struct nf_conntrack_expect *exp, *last = NULL; + struct hlist_node *next; - hlist_for_each_entry(exp, &master_help->expectations, lnode) { + hlist_for_each_entry_safe(exp, next, &master_help->expectations, lnode) { + if (nf_ct_exp_is_expired(exp)) { + nf_ct_unlink_expect(exp); + continue; + } if (exp->class == new->class) last = exp; } - if (last) - nf_ct_remove_expect(last); + /* Still worth to evict oldest expectation after garbage collection? */ + if (last && + master_help->expecting[last->class] >= p->max_expected) + nf_ct_unlink_expect(last); } static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, @@ -467,14 +472,18 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { + if (nf_ct_exp_is_expired(i)) { + nf_ct_unlink_expect(i); + continue; + } if (master_matches(i, expect, flags) && expect_matches(i, expect)) { if (i->class != expect->class || i->master != expect->master) return -EALREADY; - if (nf_ct_remove_expect(i)) - break; + nf_ct_unlink_expect(i); + break; } else if (expect_clash(i, expect)) { ret = -EBUSY; goto out; @@ -486,14 +495,8 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, if (helper) { p = &helper->expect_policy[expect->class]; if (p->max_expected && - master_help->expecting[expect->class] >= p->max_expected) { - evict_oldest_expect(master_help, expect); - if (master_help->expecting[expect->class] - >= p->max_expected) { - ret = -EMFILE; - goto out; - } - } + master_help->expecting[expect->class] >= p->max_expected) + evict_oldest_expect(master_help, expect, p); } cnet = nf_ct_pernet(net); @@ -547,10 +550,8 @@ void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, vo hlist_for_each_entry_safe(exp, next, &nf_ct_expect_hash[i], hnode) { - if (iter(exp, data) && timer_delete(&exp->timeout)) { + if (iter(exp, data)) nf_ct_unlink_expect(exp); - nf_ct_expect_put(exp); - } } } @@ -577,10 +578,8 @@ void nf_ct_expect_iterate_net(struct net *net, if (!net_eq(nf_ct_exp_net(exp), net)) continue; - if (iter(exp, data) && timer_delete(&exp->timeout)) { + if (iter(exp, data)) nf_ct_unlink_expect_report(exp, portid, report); - nf_ct_expect_put(exp); - } } } @@ -657,17 +656,17 @@ static int exp_seq_show(struct seq_file *s, void *v) struct net *net = seq_file_net(s); struct hlist_node *n = v; char *delim = ""; + __s32 timeout; expect = hlist_entry(n, struct nf_conntrack_expect, hnode); if (!net_eq(nf_ct_exp_net(expect), net)) return 0; + if (nf_ct_exp_is_expired(expect)) + return 0; - if (expect->timeout.function) - seq_printf(s, "%ld ", timer_pending(&expect->timeout) - ? (long)(expect->timeout.expires - jiffies)/HZ : 0); - else - seq_puts(s, "- "); + timeout = (__s32)(READ_ONCE(expect->timeout) - nfct_time_stamp) / HZ; + seq_printf(s, "%d ", timeout > 0 ? timeout : 0); seq_printf(s, "l3proto = %u proto=%u ", expect->tuple.src.l3num, expect->tuple.dst.protonum); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 7f189dceb3c4..24931e379985 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1388,8 +1388,8 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, "timeout to %u seconds for", info->timeout); nf_ct_dump_tuple(&exp->tuple); - mod_timer_pending(&exp->timeout, - jiffies + info->timeout * HZ); + WRITE_ONCE(exp->timeout, + nfct_time_stamp + (info->timeout * HZ)); } spin_unlock_bh(&nf_conntrack_expect_lock); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 2f35bdd0d7d7..8b94001c2430 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -181,10 +181,10 @@ nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp) struct nf_conn_help *help; help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp); - if (help) + if (help) { + __set_bit(IPS_HELPER_BIT, &ct->status); INIT_HLIST_HEAD(&help->expectations); - else - pr_debug("failed to add helper extension area"); + } return help; } EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add); @@ -203,10 +203,8 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, return 0; help = nfct_help(tmpl); - if (help != NULL) { + if (help) helper = rcu_dereference(help->helper); - set_bit(IPS_HELPER_BIT, &ct->status); - } help = nfct_help(ct); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index b429e648f06c..4e78d2482989 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3014,8 +3014,8 @@ static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) { + __s32 timeout = (__s32)(READ_ONCE(exp->timeout) - nfct_time_stamp) / HZ; struct nf_conn *master = exp->master; - long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; struct nf_conntrack_helper *helper; #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *nest_parms; @@ -3178,6 +3178,9 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], hnode) { + if (nf_ct_exp_is_expired(exp)) + continue; + if (l3proto && exp->tuple.src.l3num != l3proto) continue; @@ -3456,11 +3459,8 @@ static int ctnetlink_del_expect(struct sk_buff *skb, } /* after list removal, usage count == 1 */ - if (timer_delete(&exp->timeout)) { - nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, - nlmsg_report(info->nlh)); - nf_ct_expect_put(exp); - } + nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, + nlmsg_report(info->nlh)); spin_unlock_bh(&nf_conntrack_expect_lock); /* have to put what we 'get' above. * after this line usage count == 0 */ @@ -3484,14 +3484,10 @@ static int ctnetlink_change_expect(struct nf_conntrack_expect *x, const struct nlattr * const cda[]) { - if (cda[CTA_EXPECT_TIMEOUT]) { - if (!timer_delete(&x->timeout)) - return -ETIME; + if (cda[CTA_EXPECT_TIMEOUT]) + WRITE_ONCE(x->timeout, nfct_time_stamp + + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ); - x->timeout.expires = jiffies + - ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; - add_timer(&x->timeout); - } return 0; } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index c606d1f60b58..5ec3a4a4bbd7 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -897,11 +897,10 @@ static int refresh_signalling_expectation(struct nf_conn *ct, exp->tuple.dst.protonum != proto || exp->tuple.dst.u.udp.port != port) continue; - if (mod_timer_pending(&exp->timeout, jiffies + expires * HZ)) { - exp->flags &= ~NF_CT_EXPECT_INACTIVE; - found = 1; - break; - } + WRITE_ONCE(exp->timeout, nfct_time_stamp + (expires * HZ)); + WRITE_ONCE(exp->flags, exp->flags & ~NF_CT_EXPECT_INACTIVE); + found = 1; + break; } spin_unlock_bh(&nf_conntrack_expect_lock); return found; @@ -920,8 +919,7 @@ static void flush_expectations(struct nf_conn *ct, bool media) hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media) continue; - if (!nf_ct_remove_expect(exp)) - continue; + nf_ct_unlink_expect(exp); if (!media) break; } @@ -1413,7 +1411,6 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct), saddr, &daddr, proto, NULL, &port); - exp->timeout.expires = sip_timeout * HZ; rcu_assign_pointer(exp->assign_helper, helper); exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 25934c6f01fb..958054dd2e2e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1145,7 +1145,6 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj, help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help && refcount_inc_not_zero(&to_assign->ct_refcnt)) { rcu_assign_pointer(help->helper, to_assign); - set_bit(IPS_HELPER_BIT, &ct->status); if ((ct->status & IPS_NAT_MASK) && !nfct_seqadj(ct)) if (!nfct_seqadj_ext_add(ct)) @@ -1326,7 +1325,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj, &ct->tuplehash[!dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3, priv->l4proto, NULL, &priv->dport); - exp->timeout.expires = jiffies + priv->timeout * HZ; + exp->timeout += priv->timeout * HZ; if (nf_ct_expect_related(exp, 0) != 0) regs->verdict.code = NF_DROP; -- cgit v1.3-14-g43fede