From: Ben Skeggs bskeggs@redhat.com

commit 4cdd2450bf739bada353e82d27b00db9af8c3001 upstream.

Signed-off-by: Ben Skeggs bskeggs@redhat.com Reviewed-by: Karol Herbst kherbst@redhat.com Signed-off-by: Karol Herbst kherbst@redhat.com Link: https://gitlab.freedesktop.org/drm/nouveau/-/merge_requests/10 Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/nouveau/nvkm/falcon/base.c | 8 ++++-- drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm200.c | 31 +++++++++++++++++++++++- drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c | 2 - drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c | 2 - drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c | 2 - drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h | 2 + 6 files changed, 41 insertions(+), 6 deletions(-)

--- a/drivers/gpu/drm/nouveau/nvkm/falcon/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/base.c @@ -117,8 +117,12 @@ nvkm_falcon_disable(struct nvkm_falcon * int nvkm_falcon_reset(struct nvkm_falcon *falcon) { - nvkm_falcon_disable(falcon); - return nvkm_falcon_enable(falcon); + if (!falcon->func->reset) { + nvkm_falcon_disable(falcon); + return nvkm_falcon_enable(falcon); + } + + return falcon->func->reset(falcon); }

int --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm200.c @@ -23,9 +23,38 @@ */ #include "priv.h"

+static int +gm200_pmu_flcn_reset(struct nvkm_falcon *falcon) +{ + struct nvkm_pmu *pmu = container_of(falcon, typeof(*pmu), falcon); + + nvkm_falcon_wr32(falcon, 0x014, 0x0000ffff); + pmu->func->reset(pmu); + return nvkm_falcon_enable(falcon); +} + +const struct nvkm_falcon_func +gm200_pmu_flcn = { + .debug = 0xc08, + .fbif = 0xe00, + .load_imem = nvkm_falcon_v1_load_imem, + .load_dmem = nvkm_falcon_v1_load_dmem, + .read_dmem = nvkm_falcon_v1_read_dmem, + .bind_context = nvkm_falcon_v1_bind_context, + .wait_for_halt = nvkm_falcon_v1_wait_for_halt, + .clear_interrupt = nvkm_falcon_v1_clear_interrupt, + .set_start_addr = nvkm_falcon_v1_set_start_addr, + .start = nvkm_falcon_v1_start, + .enable = nvkm_falcon_v1_enable, + .disable = nvkm_falcon_v1_disable, + .reset = gm200_pmu_flcn_reset, + .cmdq = { 0x4a0, 0x4b0, 4 }, + .msgq = { 0x4c8, 0x4cc, 0 }, +}; + static const struct nvkm_pmu_func gm200_pmu = { - .flcn = &gt215_pmu_flcn, + .flcn = &gm200_pmu_flcn, .enabled = gf100_pmu_enabled, .reset = gf100_pmu_reset, }; --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -211,7 +211,7 @@ gm20b_pmu_recv(struct nvkm_pmu *pmu)

static const struct nvkm_pmu_func gm20b_pmu = { - .flcn = &gt215_pmu_flcn, + .flcn = &gm200_pmu_flcn, .enabled = gf100_pmu_enabled, .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c @@ -39,7 +39,7 @@ gp102_pmu_enabled(struct nvkm_pmu *pmu)

static const struct nvkm_pmu_func gp102_pmu = { - .flcn = &gt215_pmu_flcn, + .flcn = &gm200_pmu_flcn, .enabled = gp102_pmu_enabled, .reset = gp102_pmu_reset, }; --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c @@ -78,7 +78,7 @@ gp10b_pmu_acr = {

static const struct nvkm_pmu_func gp10b_pmu = { - .flcn = &gt215_pmu_flcn, + .flcn = &gm200_pmu_flcn, .enabled = gf100_pmu_enabled, .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h @@ -44,6 +44,8 @@ void gf100_pmu_reset(struct nvkm_pmu *);

void gk110_pmu_pgob(struct nvkm_pmu *, bool);

+extern const struct nvkm_falcon_func gm200_pmu_flcn; + void gm20b_pmu_acr_bld_patch(struct nvkm_acr *, u32, s64); void gm20b_pmu_acr_bld_write(struct nvkm_acr *, u32, struct nvkm_acr_lsfw *); int gm20b_pmu_acr_boot(struct nvkm_falcon *);

From: Hao Luo haoluo@google.com

commit 48946bd6a5d695c50b34546864b79c1f910a33c1 upstream.

We have introduced a new type to make bpf_arg composable, by reserving high bits of bpf_arg to represent flags of a type.

One of the flags is PTR_MAYBE_NULL which indicates a pointer may be NULL. When applying this flag to an arg_type, it means the arg can take NULL pointer. This patch switches the qualified arg_types to use this flag. The arg_types changed in this patch include:

1. ARG_PTR_TO_MAP_VALUE_OR_NULL 2. ARG_PTR_TO_MEM_OR_NULL 3. ARG_PTR_TO_CTX_OR_NULL 4. ARG_PTR_TO_SOCKET_OR_NULL 5. ARG_PTR_TO_ALLOC_MEM_OR_NULL 6. ARG_PTR_TO_STACK_OR_NULL

This patch does not eliminate the use of these arg_types, instead it makes them an alias to the 'ARG_XXX | PTR_MAYBE_NULL'.

Signed-off-by: Hao Luo haoluo@google.com Signed-off-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/bpf/20211217003152.48334-3-haoluo@google.com Cc: stable@vger.kernel.org # 5.16.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/bpf.h | 15 +++++++++------ kernel/bpf/verifier.c | 39 ++++++++++++++------------------------- 2 files changed, 23 insertions(+), 31 deletions(-)

--- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -331,13 +331,11 @@ enum bpf_arg_type { ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ - ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */

/* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ - ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */ ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, * helper function must fill all bytes or clear * them in error case. @@ -347,26 +345,31 @@ enum bpf_arg_type { ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */

ARG_PTR_TO_CTX, /* pointer to context */ - ARG_PTR_TO_CTX_OR_NULL, /* pointer to context or NULL */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ - ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ - ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ - ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ + ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX,

+ /* Extended arg_types. */ + ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, + ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, + ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, + ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, + ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, + ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, + /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -472,14 +472,9 @@ static bool arg_type_may_be_refcounted(e return type == ARG_PTR_TO_SOCK_COMMON; }

-static bool arg_type_may_be_null(enum bpf_arg_type type) +static bool type_may_be_null(u32 type) { - return type == ARG_PTR_TO_MAP_VALUE_OR_NULL || - type == ARG_PTR_TO_MEM_OR_NULL || - type == ARG_PTR_TO_CTX_OR_NULL || - type == ARG_PTR_TO_SOCKET_OR_NULL || - type == ARG_PTR_TO_ALLOC_MEM_OR_NULL || - type == ARG_PTR_TO_STACK_OR_NULL; + return type & PTR_MAYBE_NULL; }

/* Determine whether the function releases some resources allocated by another @@ -4963,9 +4958,8 @@ static int process_timer_func(struct bpf

static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { - return type == ARG_PTR_TO_MEM || - type == ARG_PTR_TO_MEM_OR_NULL || - type == ARG_PTR_TO_UNINIT_MEM; + return base_type(type) == ARG_PTR_TO_MEM || + base_type(type) == ARG_PTR_TO_UNINIT_MEM; }

static bool arg_type_is_mem_size(enum bpf_arg_type type) @@ -5102,31 +5096,26 @@ static const struct bpf_reg_types *compa [ARG_PTR_TO_MAP_KEY] = &map_key_value_types, [ARG_PTR_TO_MAP_VALUE] = &map_key_value_types, [ARG_PTR_TO_UNINIT_MAP_VALUE] = &map_key_value_types, - [ARG_PTR_TO_MAP_VALUE_OR_NULL] = &map_key_value_types, [ARG_CONST_SIZE] = &scalar_types, [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_MAP_PTR] = &const_map_ptr_types, [ARG_PTR_TO_CTX] = &context_types, - [ARG_PTR_TO_CTX_OR_NULL] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, #ifdef CONFIG_NET [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types, #endif [ARG_PTR_TO_SOCKET] = &fullsock_types, - [ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types, [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, - [ARG_PTR_TO_MEM_OR_NULL] = &mem_types, [ARG_PTR_TO_UNINIT_MEM] = &mem_types, [ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types, - [ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types, [ARG_PTR_TO_INT] = &int_ptr_types, [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, - [ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types, + [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, }; @@ -5140,7 +5129,7 @@ static int check_reg_type(struct bpf_ver const struct bpf_reg_types *compatible; int i, j;

- compatible = compatible_reg_types[arg_type]; + compatible = compatible_reg_types[base_type(arg_type)]; if (!compatible) { verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type); return -EFAULT; @@ -5221,15 +5210,14 @@ static int check_func_arg(struct bpf_ver return -EACCES; }

- if (arg_type == ARG_PTR_TO_MAP_VALUE || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || - arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { + if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE || + base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) { err = resolve_map_arg_type(env, meta, &arg_type); if (err) return err; }

- if (register_is_null(reg) && arg_type_may_be_null(arg_type)) + if (register_is_null(reg) && type_may_be_null(arg_type)) /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ @@ -5298,10 +5286,11 @@ skip_type_check: err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); - } else if (arg_type == ARG_PTR_TO_MAP_VALUE || - (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL && - !register_is_null(reg)) || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { + } else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE || + base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) { + if (type_may_be_null(arg_type) && register_is_null(reg)) + return 0; + /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */

From: Hao Luo haoluo@google.com

commit c25b2ae136039ffa820c26138ed4a5e5f3ab3841 upstream.

We have introduced a new type to make bpf_reg composable, by allocating bits in the type to represent flags.

One of the flags is PTR_MAYBE_NULL which indicates a pointer may be NULL. This patch switches the qualified reg_types to use this flag. The reg_types changed in this patch include:

1. PTR_TO_MAP_VALUE_OR_NULL 2. PTR_TO_SOCKET_OR_NULL 3. PTR_TO_SOCK_COMMON_OR_NULL 4. PTR_TO_TCP_SOCK_OR_NULL 5. PTR_TO_BTF_ID_OR_NULL 6. PTR_TO_MEM_OR_NULL 7. PTR_TO_RDONLY_BUF_OR_NULL 8. PTR_TO_RDWR_BUF_OR_NULL

[haoluo: backport notes There was a reg_type_may_be_null() in adjust_ptr_min_max_vals() in 5.16.x, but didn't exist in the upstream commit. This backport converted that reg_type_may_be_null() to type_may_be_null() as well.]

Signed-off-by: Hao Luo haoluo@google.com Signed-off-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/r/20211217003152.48334-5-haoluo@google.com Cc: stable@vger.kernel.org # 5.16.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/bpf.h | 18 +- include/linux/bpf_verifier.h | 4 kernel/bpf/btf.c | 7 - kernel/bpf/map_iter.c | 4 kernel/bpf/verifier.c | 297 ++++++++++++++++++------------------------- net/core/bpf_sk_storage.c | 2 net/core/sock_map.c | 2 7 files changed, 148 insertions(+), 186 deletions(-)

--- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -465,18 +465,15 @@ enum bpf_reg_type { PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ - PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ + PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ - PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ - PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ - PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need @@ -494,18 +491,21 @@ enum bpf_reg_type { * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ - PTR_TO_BTF_ID_OR_NULL, PTR_TO_MEM, /* reg points to valid memory region */ - PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ - PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */ PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ - PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ - PTR_TO_MAP_KEY, /* reg points to a map element key */ __BPF_REG_TYPE_MAX,

+ /* Extended reg_types. */ + PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, + PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, + PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, + PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, + PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, + PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MEM, + /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -18,6 +18,8 @@ * that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) +/* size of type_str_buf in bpf_verifier. */ +#define TYPE_STR_BUF_LEN 64

/* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that @@ -474,6 +476,8 @@ struct bpf_verifier_env { /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; bpfptr_t fd_array; + /* buffer used in reg_type_str() to generate reg_type string */ + char type_str_buf[TYPE_STR_BUF_LEN]; };

__printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4928,10 +4928,13 @@ bool btf_ctx_access(int off, int size, e /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; + u32 type, flag;

+ type = base_type(ctx_arg_info->reg_type); + flag = type_flag(ctx_arg_info->reg_type); if (ctx_arg_info->offset == off && - (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL || - ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) { + (type == PTR_TO_RDWR_BUF || type == PTR_TO_RDONLY_BUF) && + (flag & PTR_MAYBE_NULL)) { info->reg_type = ctx_arg_info->reg_type; return true; } --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_map_elem, key), - PTR_TO_RDONLY_BUF_OR_NULL }, + PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL }, { offsetof(struct bpf_iter__bpf_map_elem, value), - PTR_TO_RDWR_BUF_OR_NULL }, + PTR_TO_RDWR_BUF | PTR_MAYBE_NULL }, }, };

--- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -439,18 +439,6 @@ static bool reg_type_not_null(enum bpf_r type == PTR_TO_SOCK_COMMON; }

-static bool reg_type_may_be_null(enum bpf_reg_type type) -{ - return type == PTR_TO_MAP_VALUE_OR_NULL || - type == PTR_TO_SOCKET_OR_NULL || - type == PTR_TO_SOCK_COMMON_OR_NULL || - type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_BTF_ID_OR_NULL || - type == PTR_TO_MEM_OR_NULL || - type == PTR_TO_RDONLY_BUF_OR_NULL || - type == PTR_TO_RDWR_BUF_OR_NULL; -} - static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && @@ -459,12 +447,9 @@ static bool reg_may_point_to_spin_lock(c

static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { - return type == PTR_TO_SOCKET || - type == PTR_TO_SOCKET_OR_NULL || - type == PTR_TO_TCP_SOCK || - type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_MEM || - type == PTR_TO_MEM_OR_NULL; + return base_type(type) == PTR_TO_SOCKET || + base_type(type) == PTR_TO_TCP_SOCK || + base_type(type) == PTR_TO_MEM; }

static bool arg_type_may_be_refcounted(enum bpf_arg_type type) @@ -534,39 +519,52 @@ static bool is_cmpxchg_insn(const struct insn->imm == BPF_CMPXCHG; }

-/* string representation of 'enum bpf_reg_type' */ -static const char * const reg_type_str[] = { - [NOT_INIT] = "?", - [SCALAR_VALUE] = "inv", - [PTR_TO_CTX] = "ctx", - [CONST_PTR_TO_MAP] = "map_ptr", - [PTR_TO_MAP_VALUE] = "map_value", - [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", - [PTR_TO_STACK] = "fp", - [PTR_TO_PACKET] = "pkt", - [PTR_TO_PACKET_META] = "pkt_meta", - [PTR_TO_PACKET_END] = "pkt_end", - [PTR_TO_FLOW_KEYS] = "flow_keys", - [PTR_TO_SOCKET] = "sock", - [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", - [PTR_TO_SOCK_COMMON] = "sock_common", - [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", - [PTR_TO_TCP_SOCK] = "tcp_sock", - [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", - [PTR_TO_TP_BUFFER] = "tp_buffer", - [PTR_TO_XDP_SOCK] = "xdp_sock", - [PTR_TO_BTF_ID] = "ptr_", - [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_", - [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_", - [PTR_TO_MEM] = "mem", - [PTR_TO_MEM_OR_NULL] = "mem_or_null", - [PTR_TO_RDONLY_BUF] = "rdonly_buf", - [PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null", - [PTR_TO_RDWR_BUF] = "rdwr_buf", - [PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null", - [PTR_TO_FUNC] = "func", - [PTR_TO_MAP_KEY] = "map_key", -}; +/* string representation of 'enum bpf_reg_type' + * + * Note that reg_type_str() can not appear more than once in a single verbose() + * statement. + */ +static const char *reg_type_str(struct bpf_verifier_env *env, + enum bpf_reg_type type) +{ + char postfix[16] = {0}; + static const char * const str[] = { + [NOT_INIT] = "?", + [SCALAR_VALUE] = "inv", + [PTR_TO_CTX] = "ctx", + [CONST_PTR_TO_MAP] = "map_ptr", + [PTR_TO_MAP_VALUE] = "map_value", + [PTR_TO_STACK] = "fp", + [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", + [PTR_TO_PACKET_END] = "pkt_end", + [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCK_COMMON] = "sock_common", + [PTR_TO_TCP_SOCK] = "tcp_sock", + [PTR_TO_TP_BUFFER] = "tp_buffer", + [PTR_TO_XDP_SOCK] = "xdp_sock", + [PTR_TO_BTF_ID] = "ptr_", + [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_", + [PTR_TO_MEM] = "mem", + [PTR_TO_RDONLY_BUF] = "rdonly_buf", + [PTR_TO_RDWR_BUF] = "rdwr_buf", + [PTR_TO_FUNC] = "func", + [PTR_TO_MAP_KEY] = "map_key", + }; + + if (type & PTR_MAYBE_NULL) { + if (base_type(type) == PTR_TO_BTF_ID || + base_type(type) == PTR_TO_PERCPU_BTF_ID) + strncpy(postfix, "or_null_", 16); + else + strncpy(postfix, "_or_null", 16); + } + + snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s", + str[base_type(type)], postfix); + return env->type_str_buf; +}

static char slot_type_char[] = { [STACK_INVALID] = '?', @@ -631,7 +629,7 @@ static void print_verifier_state(struct continue; verbose(env, " R%d", i); print_liveness(env, reg->live); - verbose(env, "=%s", reg_type_str[t]); + verbose(env, "=%s", reg_type_str(env, t)); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && @@ -639,9 +637,8 @@ static void print_verifier_state(struct /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%lld", reg->var_off.value + reg->off); } else { - if (t == PTR_TO_BTF_ID || - t == PTR_TO_BTF_ID_OR_NULL || - t == PTR_TO_PERCPU_BTF_ID) + if (base_type(t) == PTR_TO_BTF_ID || + base_type(t) == PTR_TO_PERCPU_BTF_ID) verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) @@ -650,10 +647,9 @@ static void print_verifier_state(struct verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) verbose(env, ",r=%d", reg->range); - else if (t == CONST_PTR_TO_MAP || - t == PTR_TO_MAP_KEY || - t == PTR_TO_MAP_VALUE || - t == PTR_TO_MAP_VALUE_OR_NULL) + else if (base_type(t) == CONST_PTR_TO_MAP || + base_type(t) == PTR_TO_MAP_KEY || + base_type(t) == PTR_TO_MAP_VALUE) verbose(env, ",ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); @@ -723,7 +719,7 @@ static void print_verifier_state(struct if (is_spilled_reg(&state->stack[i])) { reg = &state->stack[i].spilled_ptr; t = reg->type; - verbose(env, "=%s", reg_type_str[t]); + verbose(env, "=%s", reg_type_str(env, t)); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) @@ -1136,8 +1132,7 @@ static void mark_reg_known_zero(struct b

static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) { - switch (reg->type) { - case PTR_TO_MAP_VALUE_OR_NULL: { + if (base_type(reg->type) == PTR_TO_MAP_VALUE) { const struct bpf_map *map = reg->map_ptr;

if (map->inner_map_meta) { @@ -1156,32 +1151,10 @@ static void mark_ptr_not_null_reg(struct } else { reg->type = PTR_TO_MAP_VALUE; } - break; - } - case PTR_TO_SOCKET_OR_NULL: - reg->type = PTR_TO_SOCKET; - break; - case PTR_TO_SOCK_COMMON_OR_NULL: - reg->type = PTR_TO_SOCK_COMMON; - break; - case PTR_TO_TCP_SOCK_OR_NULL: - reg->type = PTR_TO_TCP_SOCK; - break; - case PTR_TO_BTF_ID_OR_NULL: - reg->type = PTR_TO_BTF_ID; - break; - case PTR_TO_MEM_OR_NULL: - reg->type = PTR_TO_MEM; - break; - case PTR_TO_RDONLY_BUF_OR_NULL: - reg->type = PTR_TO_RDONLY_BUF; - break; - case PTR_TO_RDWR_BUF_OR_NULL: - reg->type = PTR_TO_RDWR_BUF; - break; - default: - WARN_ONCE(1, "unknown nullable register type"); + return; } + + reg->type &= ~PTR_MAYBE_NULL; }

static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) @@ -2042,7 +2015,7 @@ static int mark_reg_read(struct bpf_veri break; if (parent->live & REG_LIVE_DONE) { verbose(env, "verifier BUG type %s var_off %lld off %d\n", - reg_type_str[parent->type], + reg_type_str(env, parent->type), parent->var_off.value, parent->off); return -EFAULT; } @@ -2701,9 +2674,8 @@ static int mark_chain_precision_stack(st

static bool is_spillable_regtype(enum bpf_reg_type type) { - switch (type) { + switch (base_type(type)) { case PTR_TO_MAP_VALUE: - case PTR_TO_MAP_VALUE_OR_NULL: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: @@ -2712,21 +2684,14 @@ static bool is_spillable_regtype(enum bp case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_BTF_ID_OR_NULL: case PTR_TO_RDONLY_BUF: - case PTR_TO_RDONLY_BUF_OR_NULL: case PTR_TO_RDWR_BUF: - case PTR_TO_RDWR_BUF_OR_NULL: case PTR_TO_PERCPU_BTF_ID: case PTR_TO_MEM: - case PTR_TO_MEM_OR_NULL: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: return true; @@ -3567,7 +3532,7 @@ static int check_ctx_access(struct bpf_v */ *reg_type = info.reg_type;

- if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) { + if (base_type(*reg_type) == PTR_TO_BTF_ID) { *btf = info.btf; *btf_id = info.btf_id; } else { @@ -3635,7 +3600,7 @@ static int check_sock_access(struct bpf_ }

verbose(env, "R%d invalid %s access off=%d size=%d\n", - regno, reg_type_str[reg->type], off, size); + regno, reg_type_str(env, reg->type), off, size);

return -EACCES; } @@ -4400,7 +4365,7 @@ static int check_mem_access(struct bpf_v } else { mark_reg_known_zero(env, regs, value_regno); - if (reg_type_may_be_null(reg_type)) + if (type_may_be_null(reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the @@ -4408,8 +4373,7 @@ static int check_mem_access(struct bpf_v * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; - if (reg_type == PTR_TO_BTF_ID || - reg_type == PTR_TO_BTF_ID_OR_NULL) { + if (base_type(reg_type) == PTR_TO_BTF_ID) { regs[value_regno].btf = btf; regs[value_regno].btf_id = btf_id; } @@ -4462,7 +4426,7 @@ static int check_mem_access(struct bpf_v } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", - regno, reg_type_str[reg->type]); + regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_sock_access(env, insn_idx, regno, off, size, t); @@ -4481,7 +4445,7 @@ static int check_mem_access(struct bpf_v } else if (reg->type == PTR_TO_RDONLY_BUF) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", - regno, reg_type_str[reg->type]); + regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_buffer_access(env, reg, regno, off, size, false, @@ -4497,7 +4461,7 @@ static int check_mem_access(struct bpf_v mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EACCES; }

@@ -4571,7 +4535,7 @@ static int check_atomic(struct bpf_verif is_sk_reg(env, insn->dst_reg)) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, - reg_type_str[reg_state(env, insn->dst_reg)->type]); + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; }

@@ -4797,9 +4761,9 @@ static int check_helper_mem_access(struc register_is_null(reg)) return 0;

- verbose(env, "R%d type=%s expected=%s\n", regno, - reg_type_str[reg->type], - reg_type_str[PTR_TO_STACK]); + verbose(env, "R%d type=%s ", regno, + reg_type_str(env, reg->type)); + verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK)); return -EACCES; } } @@ -4810,7 +4774,7 @@ int check_mem_reg(struct bpf_verifier_en if (register_is_null(reg)) return 0;

- if (reg_type_may_be_null(reg->type)) { + if (type_may_be_null(reg->type)) { /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. @@ -5144,10 +5108,10 @@ static int check_reg_type(struct bpf_ver goto found; }

- verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]); + verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, type)); for (j = 0; j + 1 < i; j++) - verbose(env, "%s, ", reg_type_str[compatible->types[j]]); - verbose(env, "%s\n", reg_type_str[compatible->types[j]]); + verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); + verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); return -EACCES;

found: @@ -6376,6 +6340,7 @@ static int check_helper_call(struct bpf_ { const struct bpf_func_proto *fn = NULL; enum bpf_return_type ret_type; + enum bpf_type_flag ret_flag; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; int insn_idx = *insn_idx_p; @@ -6510,6 +6475,7 @@ static int check_helper_call(struct bpf_

/* update return register (already marked as written above) */ ret_type = fn->ret_type; + ret_flag = type_flag(fn->ret_type); if (ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); @@ -6529,25 +6495,23 @@ static int check_helper_call(struct bpf_ } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].map_uid = meta.map_uid; - if (type_may_be_null(ret_type)) { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; - } else { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; - if (map_value_has_spin_lock(meta.map_ptr)) - regs[BPF_REG_0].id = ++env->id_gen; + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; + if (!type_may_be_null(ret_type) && + map_value_has_spin_lock(meta.map_ptr)) { + regs[BPF_REG_0].id = ++env->id_gen; } } else if (base_type(ret_type) == RET_PTR_TO_SOCKET) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag; } else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag; } else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag; } else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = meta.mem_size; } else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) { const struct btf_type *t; @@ -6567,14 +6531,10 @@ static int check_helper_call(struct bpf_ tname, PTR_ERR(ret)); return -EINVAL; } - regs[BPF_REG_0].type = - (ret_type & PTR_MAYBE_NULL) ? - PTR_TO_MEM_OR_NULL : PTR_TO_MEM; + regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = tsize; } else { - regs[BPF_REG_0].type = - (ret_type & PTR_MAYBE_NULL) ? - PTR_TO_BTF_ID_OR_NULL : PTR_TO_BTF_ID; + regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } @@ -6582,9 +6542,7 @@ static int check_helper_call(struct bpf_ int ret_btf_id;

mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = (ret_type & PTR_MAYBE_NULL) ? - PTR_TO_BTF_ID_OR_NULL : - PTR_TO_BTF_ID; + regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; ret_btf_id = *fn->ret_btf_id; if (ret_btf_id == 0) { verbose(env, "invalid return type %u of func %s#%d\n", @@ -6603,7 +6561,7 @@ static int check_helper_call(struct bpf_ return -EINVAL; }

- if (reg_type_may_be_null(regs[BPF_REG_0].type)) + if (type_may_be_null(regs[BPF_REG_0].type)) regs[BPF_REG_0].id = ++env->id_gen;

if (is_ptr_cast_function(func_id)) { @@ -6812,25 +6770,25 @@ static bool check_reg_sane_offset(struct

if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "math between %s pointer and %lld is not allowed\n", - reg_type_str[type], val); + reg_type_str(env, type), val); return false; }

if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) { verbose(env, "%s pointer offset %d is not allowed\n", - reg_type_str[type], reg->off); + reg_type_str(env, type), reg->off); return false; }

if (smin == S64_MIN) { verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", - reg_type_str[type]); + reg_type_str(env, type)); return false; }

if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", - smin, reg_type_str[type]); + smin, reg_type_str(env, type)); return false; }

@@ -7207,11 +7165,13 @@ static int adjust_ptr_min_max_vals(struc return -EACCES; }

- switch (ptr_reg->type) { - case PTR_TO_MAP_VALUE_OR_NULL: + if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", - dst, reg_type_str[ptr_reg->type]); + dst, reg_type_str(env, ptr_reg->type)); return -EACCES; + } + + switch (base_type(ptr_reg->type)) { case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) @@ -7224,10 +7184,10 @@ static int adjust_ptr_min_max_vals(struc case PTR_TO_XDP_SOCK: reject: verbose(env, "R%d pointer arithmetic on %s prohibited\n", - dst, reg_type_str[ptr_reg->type]); + dst, reg_type_str(env, ptr_reg->type)); return -EACCES; default: - if (reg_type_may_be_null(ptr_reg->type)) + if (type_may_be_null(ptr_reg->type)) goto reject; break; } @@ -8949,7 +8909,7 @@ static void mark_ptr_or_null_reg(struct struct bpf_reg_state *reg, u32 id, bool is_null) { - if (reg_type_may_be_null(reg->type) && reg->id == id && + if (type_may_be_null(reg->type) && reg->id == id && !WARN_ON_ONCE(!reg->id)) { if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0) || @@ -9327,7 +9287,7 @@ static int check_cond_jmp_op(struct bpf_ */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && - reg_type_may_be_null(dst_reg->type)) { + type_may_be_null(dst_reg->type)) { /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ @@ -9584,7 +9544,7 @@ static int check_return_code(struct bpf_ /* enforce return zero from async callbacks like timer */ if (reg->type != SCALAR_VALUE) { verbose(env, "In async callback the register R0 is not a known value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; }

@@ -9598,7 +9558,7 @@ static int check_return_code(struct bpf_ if (is_subprog) { if (reg->type != SCALAR_VALUE) { verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; } return 0; @@ -9662,7 +9622,7 @@ static int check_return_code(struct bpf_

if (reg->type != SCALAR_VALUE) { verbose(env, "At program exit the register R0 is not a known value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; }

@@ -10443,7 +10403,7 @@ static bool regsafe(struct bpf_verifier_ return true; if (rcur->type == NOT_INIT) return false; - switch (rold->type) { + switch (base_type(rold->type)) { case SCALAR_VALUE: if (env->explore_alu_limits) return false; @@ -10465,6 +10425,22 @@ static bool regsafe(struct bpf_verifier_ } case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: + /* a PTR_TO_MAP_VALUE could be safe to use as a + * PTR_TO_MAP_VALUE_OR_NULL into the same map. + * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- + * checked, doing so could have affected others with the same + * id, and we can't check for that because we lost the id when + * we converted to a PTR_TO_MAP_VALUE. + */ + if (type_may_be_null(rold->type)) { + if (!type_may_be_null(rcur->type)) + return false; + if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) + return false; + /* Check our ids match any regs they're supposed to */ + return check_ids(rold->id, rcur->id, idmap); + } + /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. * 'id' is not compared, since it's only used for maps with @@ -10476,20 +10452,6 @@ static bool regsafe(struct bpf_verifier_ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); - case PTR_TO_MAP_VALUE_OR_NULL: - /* a PTR_TO_MAP_VALUE could be safe to use as a - * PTR_TO_MAP_VALUE_OR_NULL into the same map. - * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- - * checked, doing so could have affected others with the same - * id, and we can't check for that because we lost the id when - * we converted to a PTR_TO_MAP_VALUE. - */ - if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL) - return false; - if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) - return false; - /* Check our ids match any regs they're supposed to */ - return check_ids(rold->id, rcur->id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: if (rcur->type != rold->type) @@ -10518,11 +10480,8 @@ static bool regsafe(struct bpf_verifier_ case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: /* Only valid matches are exact, which memcmp() above * would have accepted @@ -11048,17 +11007,13 @@ next: /* Return true if it's OK to have the same insn return a different type. */ static bool reg_type_mismatch_ok(enum bpf_reg_type type) { - switch (type) { + switch (base_type(type)) { case PTR_TO_CTX: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_BTF_ID_OR_NULL: return false; default: return true; @@ -11282,7 +11237,7 @@ static int do_check(struct bpf_verifier_ if (is_ctx_reg(env, insn->dst_reg)) { verbose(env, "BPF_ST stores into R%d %s is not allowed\n", insn->dst_reg, - reg_type_str[reg_state(env, insn->dst_reg)->type]); + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; }

--- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -929,7 +929,7 @@ static struct bpf_iter_reg bpf_sk_storag { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), PTR_TO_BTF_ID_OR_NULL }, { offsetof(struct bpf_iter__bpf_sk_storage_map, value), - PTR_TO_RDWR_BUF_OR_NULL }, + PTR_TO_RDWR_BUF | PTR_MAYBE_NULL }, }, .seq_info = &iter_seq_info, }; --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1569,7 +1569,7 @@ static struct bpf_iter_reg sock_map_iter .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__sockmap, key), - PTR_TO_RDONLY_BUF_OR_NULL }, + PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL }, { offsetof(struct bpf_iter__sockmap, sk), PTR_TO_BTF_ID_OR_NULL }, },

From: Hao Luo haoluo@google.com

commit cf9f2f8d62eca810afbd1ee6cc0800202b000e57 upstream.

Remove PTR_TO_MEM_OR_NULL and replace it with PTR_TO_MEM combined with flag PTR_MAYBE_NULL.

Signed-off-by: Hao Luo haoluo@google.com Signed-off-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/bpf/20211217003152.48334-7-haoluo@google.com Cc: stable@vger.kernel.org # 5.16.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/bpf.h | 1 - kernel/bpf/btf.c | 2 +- kernel/bpf/verifier.c | 2 +- 3 files changed, 2 insertions(+), 3 deletions(-)

--- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -506,7 +506,6 @@ enum bpf_reg_type { PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, - PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MEM,

/* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5847,7 +5847,7 @@ int btf_prepare_func_args(struct bpf_ver return -EINVAL; }

- reg->type = PTR_TO_MEM_OR_NULL; + reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; reg->id = ++env->id_gen;

continue; --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13336,7 +13336,7 @@ static int do_check_common(struct bpf_ve mark_reg_known_zero(env, regs, i); else if (regs[i].type == SCALAR_VALUE) mark_reg_unknown(env, regs, i); - else if (regs[i].type == PTR_TO_MEM_OR_NULL) { + else if (base_type(regs[i].type) == PTR_TO_MEM) { const u32 mem_size = regs[i].mem_size;

mark_reg_known_zero(env, regs, i);

From: Hao Luo haoluo@google.com

commit 216e3cd2f28dbbf1fe86848e0e29e6693b9f0a20 upstream.

Some helper functions may modify its arguments, for example, bpf_d_path, bpf_get_stack etc. Previously, their argument types were marked as ARG_PTR_TO_MEM, which is compatible with read-only mem types, such as PTR_TO_RDONLY_BUF. Therefore it's legitimate, but technically incorrect, to modify a read-only memory by passing it into one of such helper functions.

This patch tags the bpf_args compatible with immutable memory with MEM_RDONLY flag. The arguments that don't have this flag will be only compatible with mutable memory types, preventing the helper from modifying a read-only memory. The bpf_args that have MEM_RDONLY are compatible with both mutable memory and immutable memory.

Signed-off-by: Hao Luo haoluo@google.com Signed-off-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/bpf/20211217003152.48334-9-haoluo@google.com Cc: stable@vger.kernel.org # 5.16.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/bpf.h | 4 ++ kernel/bpf/btf.c | 2 - kernel/bpf/cgroup.c | 2 - kernel/bpf/helpers.c | 8 ++--- kernel/bpf/ringbuf.c | 2 - kernel/bpf/syscall.c | 2 - kernel/bpf/verifier.c | 20 ++++++++++++-- kernel/trace/bpf_trace.c | 26 +++++++++---------- net/core/filter.c | 64 +++++++++++++++++++++++------------------------ 9 files changed, 73 insertions(+), 57 deletions(-)

--- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -311,7 +311,9 @@ enum bpf_type_flag { /* PTR may be NULL. */ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS),

- /* MEM is read-only. */ + /* MEM is read-only. When applied on bpf_arg, it indicates the arg is + * compatible with both mutable and immutable memory. + */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS),

__BPF_TYPE_LAST_FLAG = MEM_RDONLY, --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6337,7 +6337,7 @@ const struct bpf_func_proto bpf_btf_find .func = bpf_btf_find_by_name_kind, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1789,7 +1789,7 @@ static const struct bpf_func_proto bpf_s .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, };

--- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -530,7 +530,7 @@ const struct bpf_func_proto bpf_strtol_p .func = bpf_strtol, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, @@ -558,7 +558,7 @@ const struct bpf_func_proto bpf_strtoul_ .func = bpf_strtoul, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, @@ -630,7 +630,7 @@ const struct bpf_func_proto bpf_event_ou .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -1011,7 +1011,7 @@ const struct bpf_func_proto bpf_snprintf .arg1_type = ARG_PTR_TO_MEM_OR_NULL, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_CONST_STR, - .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

--- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -444,7 +444,7 @@ const struct bpf_func_proto bpf_ringbuf_ .func = bpf_ringbuf_output, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4772,7 +4772,7 @@ static const struct bpf_func_proto bpf_s .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, };

--- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5060,7 +5060,6 @@ static const struct bpf_reg_types mem_ty PTR_TO_MAP_VALUE, PTR_TO_MEM, PTR_TO_BUF, - PTR_TO_BUF | MEM_RDONLY, }, };

@@ -5130,6 +5129,21 @@ static int check_reg_type(struct bpf_ver return -EFAULT; }

+ /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY, + * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY + * + * Same for MAYBE_NULL: + * + * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL, + * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL + * + * Therefore we fold these flags depending on the arg_type before comparison. + */ + if (arg_type & MEM_RDONLY) + type &= ~MEM_RDONLY; + if (arg_type & PTR_MAYBE_NULL) + type &= ~PTR_MAYBE_NULL; + for (i = 0; i < ARRAY_SIZE(compatible->types); i++) { expected = compatible->types[i]; if (expected == NOT_INIT) @@ -5139,14 +5153,14 @@ static int check_reg_type(struct bpf_ver goto found; }

- verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, type)); + verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type)); for (j = 0; j + 1 < i; j++) verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); return -EACCES;

found: - if (type == PTR_TO_BTF_ID) { + if (reg->type == PTR_TO_BTF_ID) { if (!arg_btf_id) { if (!compatible->btf_id) { verbose(env, "verifier internal error: missing arg compatible BTF ID\n"); --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_p .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, };

@@ -394,7 +394,7 @@ static const struct bpf_func_proto bpf_t .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, };

@@ -450,9 +450,9 @@ static const struct bpf_func_proto bpf_t .func = bpf_trace_vprintk, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, - .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -492,9 +492,9 @@ static const struct bpf_func_proto bpf_s .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, - .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -509,7 +509,7 @@ static const struct bpf_func_proto bpf_s .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -533,7 +533,7 @@ static const struct bpf_func_proto bpf_s .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -694,7 +694,7 @@ static const struct bpf_func_proto bpf_p .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -1004,7 +1004,7 @@ const struct bpf_func_proto bpf_snprintf .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; @@ -1285,7 +1285,7 @@ static const struct bpf_func_proto bpf_p .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -1507,7 +1507,7 @@ static const struct bpf_func_proto bpf_p .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -1561,7 +1561,7 @@ static const struct bpf_func_proto bpf_g .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1713,7 +1713,7 @@ static const struct bpf_func_proto bpf_s .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; @@ -2018,9 +2018,9 @@ static const struct bpf_func_proto bpf_c .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM_OR_NULL, + .arg1_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, - .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; @@ -2541,7 +2541,7 @@ static const struct bpf_func_proto bpf_r .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM_OR_NULL, + .arg2_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -4174,7 +4174,7 @@ static const struct bpf_func_proto bpf_s .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -4188,7 +4188,7 @@ const struct bpf_func_proto bpf_skb_outp .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -4371,7 +4371,7 @@ static const struct bpf_func_proto bpf_s .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; @@ -4397,7 +4397,7 @@ static const struct bpf_func_proto bpf_s .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, };

@@ -4567,7 +4567,7 @@ static const struct bpf_func_proto bpf_x .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -4581,7 +4581,7 @@ const struct bpf_func_proto bpf_xdp_outp .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

@@ -5069,7 +5069,7 @@ const struct bpf_func_proto bpf_sk_setso .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, };

@@ -5103,7 +5103,7 @@ static const struct bpf_func_proto bpf_s .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, };

@@ -5137,7 +5137,7 @@ static const struct bpf_func_proto bpf_s .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, };

@@ -5312,7 +5312,7 @@ static const struct bpf_func_proto bpf_b .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, };

@@ -5900,7 +5900,7 @@ static const struct bpf_func_proto bpf_l .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE };

@@ -5910,7 +5910,7 @@ static const struct bpf_func_proto bpf_l .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE };

@@ -5953,7 +5953,7 @@ static const struct bpf_func_proto bpf_l .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE };

@@ -6041,7 +6041,7 @@ static const struct bpf_func_proto bpf_l .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE };

@@ -6266,7 +6266,7 @@ static const struct bpf_func_proto bpf_s .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6285,7 +6285,7 @@ static const struct bpf_func_proto bpf_s .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6304,7 +6304,7 @@ static const struct bpf_func_proto bpf_s .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6341,7 +6341,7 @@ static const struct bpf_func_proto bpf_x .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6364,7 +6364,7 @@ static const struct bpf_func_proto bpf_x .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6387,7 +6387,7 @@ static const struct bpf_func_proto bpf_x .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6406,7 +6406,7 @@ static const struct bpf_func_proto bpf_s .gpl_only = false, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6425,7 +6425,7 @@ static const struct bpf_func_proto bpf_s .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6444,7 +6444,7 @@ static const struct bpf_func_proto bpf_s .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6757,9 +6757,9 @@ static const struct bpf_func_proto bpf_t .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, };

@@ -6826,9 +6826,9 @@ static const struct bpf_func_proto bpf_t .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, };

@@ -7057,7 +7057,7 @@ static const struct bpf_func_proto bpf_s .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, };

From: Sergio Costas rastersoft@gmail.com

commit fd5dd6acd8f823ea804f76d3af64fa1be9d5fb78 upstream.

This patch adds support for the UGTABLET WP5540 digitizer tablet devices. Without it, the pen moves the cursor, but neither the buttons nor the tap sensor in the tip do work.

Signed-off-by: Sergio Costas rastersoft@gmail.com Link: https://lore.kernel.org/r/63dece1d-91ca-1b1b-d90d-335be66896be@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-quirks.c | 1 + 2 files changed, 2 insertions(+)

--- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -1365,6 +1365,7 @@ #define USB_VENDOR_ID_UGTIZER 0x2179 #define USB_DEVICE_ID_UGTIZER_TABLET_GP0610 0x0053 #define USB_DEVICE_ID_UGTIZER_TABLET_GT5040 0x0077 +#define USB_DEVICE_ID_UGTIZER_TABLET_WP5540 0x0004

#define USB_VENDOR_ID_VIEWSONIC 0x0543 #define USB_DEVICE_ID_VIEWSONIC_PD1011 0xe621 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -187,6 +187,7 @@ static const struct hid_device_id hid_qu { HID_USB_DEVICE(USB_VENDOR_ID_TURBOX, USB_DEVICE_ID_TURBOX_KEYBOARD), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_KNA5), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_TWA60), HID_QUIRK_MULTI_INPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_WP5540), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_MEDIA_TABLET_10_6_INCH), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_MEDIA_TABLET_14_1_INCH), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SIRIUS_BATTERY_FREE_TABLET), HID_QUIRK_MULTI_INPUT },

From: Helge Deller deller@gmx.de

commit b160628e9ebcdc85d0db9d7f423c26b3c7c179d0 upstream.

It happens quite often that people use the wrong compiler to build the kernel:

make ARCH=parisc -> builds the 32-bit kernel make ARCH=parisc64 -> builds the 64-bit kernel

This patch adds a sanity check which errors out with an instruction how use the correct ARCH= option.

Signed-off-by: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org # v5.15+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/parisc/include/asm/bitops.h | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -12,6 +12,14 @@ #include <asm/barrier.h> #include <linux/atomic.h>

+/* compiler build environment sanity checks: */ +#if !defined(CONFIG_64BIT) && defined(__LP64__) +#error "Please use 'ARCH=parisc' to build the 32-bit kernel." +#endif +#if defined(CONFIG_64BIT) && !defined(__LP64__) +#error "Please use 'ARCH=parisc64' to build the 64-bit kernel." +#endif + /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion * on use of volatile and __*_bit() (set/clear/change): * *_bit() want use of volatile.

From: John David Anglin dave.anglin@bell.net

commit 9129886b88185962538180625ca8051362b01327 upstream.

With huge kernel pages, we randomly eat a SPARC in map_pages(). This is fixed by dropping __init from the declaration.

However, map_pages references the __init routine memblock_alloc_try_nid via memblock_alloc. Thus, it needs to be marked with __ref.

memblock_alloc is only called before the kernel text is set to readonly.

The __ref on free_initmem is no longer needed.

Comment regarding map_pages being in the init section is removed.

Signed-off-by: John David Anglin dave.anglin@bell.net Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/parisc/mm/init.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

--- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -337,9 +337,9 @@ static void __init setup_bootmem(void)

static bool kernel_set_to_readonly;

-static void __init map_pages(unsigned long start_vaddr, - unsigned long start_paddr, unsigned long size, - pgprot_t pgprot, int force) +static void __ref map_pages(unsigned long start_vaddr, + unsigned long start_paddr, unsigned long size, + pgprot_t pgprot, int force) { pmd_t *pmd; pte_t *pg_table; @@ -449,7 +449,7 @@ void __init set_kernel_text_rw(int enabl flush_tlb_all(); }

-void __ref free_initmem(void) +void free_initmem(void) { unsigned long init_begin = (unsigned long)__init_begin; unsigned long init_end = (unsigned long)__init_end; @@ -463,7 +463,6 @@ void __ref free_initmem(void) /* The init text pages are marked R-X. We have to * flush the icache and mark them RW- * - * This is tricky, because map_pages is in the init section. * Do a dummy remap of the data section first (the data * section is already PAGE_KERNEL) to pull in the TLB entries * for map_kernel */

From: John David Anglin dave.anglin@bell.net

commit d7da660cab47183cded65e11b64497d0f56c6edf upstream.

This patch implements the same bug fix to ccio-dma.c as to sba_iommu.c. It ensures that only the allocated entries of the sglist are accessed.

Signed-off-by: John David Anglin dave.anglin@bell.net Cc: stable@vger.kernel.org Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/parisc/ccio-dma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -1003,7 +1003,7 @@ ccio_unmap_sg(struct device *dev, struct ioc->usg_calls++; #endif

- while(sg_dma_len(sglist) && nents--) { + while (nents && sg_dma_len(sglist)) {

#ifdef CCIO_COLLECT_STATS ioc->usg_pages += sg_dma_len(sglist) >> PAGE_SHIFT; @@ -1011,6 +1011,7 @@ ccio_unmap_sg(struct device *dev, struct ccio_unmap_page(dev, sg_dma_address(sglist), sg_dma_len(sglist), direction, 0); ++sglist; + nents--; }

DBG_RUN_SG("%s() DONE (nents %d)\n", __func__, nents);

From: Linus Torvalds torvalds@linux-foundation.org

commit 80d47f5de5e311cbc0d01ebb6ee684e8f4c196c6 upstream.

Oded Gabbay reports that enabling NUMA balancing causes corruption with his Gaudi accelerator test load:

"All the details are in the bug, but the bottom line is that somehow, this patch causes corruption when the numa balancing feature is enabled AND we don't use process affinity AND we use GUP to pin pages so our accelerator can DMA to/from system memory.

Either disabling numa balancing, using process affinity to bind to specific numa-node or reverting this patch causes the bug to disappear"

and Oded bisected the issue to commit 09854ba94c6a ("mm: do_wp_page() simplification").

Now, the NUMA balancing shouldn't actually be changing the writability of a page, and as such shouldn't matter for COW. But it appears it does. Suspicious.

However, regardless of that, the condition for enabling NUMA faults in change_pte_range() is nonsensical. It uses "page_mapcount(page)" to decide if a COW page should be NUMA-protected or not, and that makes absolutely no sense.

The number of mappings a page has is irrelevant: not only does GUP get a reference to a page as in Oded's case, but the other mappings migth be paged out and the only reference to them would be in the page count.

Since we should never try to NUMA-balance a page that we can't move anyway due to other references, just fix the code to use 'page_count()'. Oded confirms that that fixes his issue.

Now, this does imply that something in NUMA balancing ends up changing page protections (other than the obvious one of making the page inaccessible to get the NUMA faulting information). Otherwise the COW simplification wouldn't matter - since doing the GUP on the page would make sure it's writable.

The cause of that permission change would be good to figure out too, since it clearly results in spurious COW events - but fixing the nonsensical test that just happened to work before is obviously the CorrectThing(tm) to do regardless.

Fixes: 09854ba94c6a ("mm: do_wp_page() simplification") Link: https://bugzilla.kernel.org/show_bug.cgi?id=215616 Link: https://lore.kernel.org/all/CAFCwf10eNmwq2wD71xjUhqkvv5+_pJMR1nPug2RqNDcFT4H... Reported-and-tested-by: Oded Gabbay oded.gabbay@gmail.com Cc: David Hildenbrand david@redhat.com Cc: Peter Xu peterx@redhat.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/mprotect.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -94,7 +94,7 @@ static unsigned long change_pte_range(st

/* Also skip shared copy-on-write pages */ if (is_cow_mapping(vma->vm_flags) && - page_mapcount(page) != 1) + page_count(page) != 1) continue;

/*

From: Daniel Thompson daniel.thompson@linaro.org

commit 2787710f73fcce4a9bdab540aaf1aef778a27462 upstream.

I'm was on the receiving end of a lockdep splat from this driver and after scratching my head I couldn't be entirely sure it was a false positive given we would also have to think about whether the regulator locking is safe (since the notifier is called whilst holding regulator locks which are also needed for regulator_is_enabled() ).

Regardless of whether it is a real bug or not, the mutex isn't needed. We can use reference counting tricks instead to avoid races with the notifier calls.

The observed splat follows:

------------------------------------------------------ kworker/u16:3/127 is trying to acquire lock: ffff00008021fb20 (&ihid_goodix->regulator_mutex){+.+.}-{4:4}, at: ihid_goodix_vdd_notify+0x30/0x94

but task is already holding lock: ffff0000835c60c0 (&(&rdev->notifier)->rwsem){++++}-{4:4}, at: blocking_notifier_call_chain+0x30/0x70

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&(&rdev->notifier)->rwsem){++++}-{4:4}: down_write+0x68/0x8c blocking_notifier_chain_register+0x54/0x70 regulator_register_notifier+0x1c/0x24 devm_regulator_register_notifier+0x58/0x98 i2c_hid_of_goodix_probe+0xdc/0x158 i2c_device_probe+0x25d/0x270 really_probe+0x174/0x2cc __driver_probe_device+0xc0/0xd8 driver_probe_device+0x50/0xe4 __device_attach_driver+0xa8/0xc0 bus_for_each_drv+0x9c/0xc0 __device_attach_async_helper+0x6c/0xbc async_run_entry_fn+0x38/0x100 process_one_work+0x294/0x438 worker_thread+0x180/0x258 kthread+0x120/0x130 ret_from_fork+0x10/0x20

-> #0 (&ihid_goodix->regulator_mutex){+.+.}-{4:4}: __lock_acquire+0xd24/0xfe8 lock_acquire+0x288/0x2f4 __mutex_lock+0xa0/0x338 mutex_lock_nested+0x3c/0x5c ihid_goodix_vdd_notify+0x30/0x94 notifier_call_chain+0x6c/0x8c blocking_notifier_call_chain+0x48/0x70 _notifier_call_chain.isra.0+0x18/0x20 _regulator_enable+0xc0/0x178 regulator_enable+0x40/0x7c goodix_i2c_hid_power_up+0x18/0x20 i2c_hid_core_power_up.isra.0+0x1c/0x2c i2c_hid_core_probe+0xd8/0x3d4 i2c_hid_of_goodix_probe+0x14c/0x158 i2c_device_probe+0x25c/0x270 really_probe+0x174/0x2cc __driver_probe_device+0xc0/0xd8 driver_probe_device+0x50/0xe4 __device_attach_driver+0xa8/0xc0 bus_for_each_drv+0x9c/0xc0 __device_attach_async_helper+0x6c/0xbc async_run_entry_fn+0x38/0x100 process_one_work+0x294/0x438 worker_thread+0x180/0x258 kthread+0x120/0x130 ret_from_fork+0x10/0x20

other info that might help us debug this:

Possible unsafe locking scenario:

CPU0 CPU1 ---- ---- lock(&(&rdev->notifier)->rwsem); lock(&ihid_goodix->regulator_mutex); lock(&(&rdev->notifier)->rwsem); lock(&ihid_goodix->regulator_mutex);

*** DEADLOCK ***

Signed-off-by: Daniel Thompson daniel.thompson@linaro.org Fixes: 18eeef46d359 ("HID: i2c-hid: goodix: Tie the reset line to true state of the regulator") Reviewed-by: Douglas Anderson dianders@chromium.org Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/i2c-hid/i2c-hid-of-goodix.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-)

--- a/drivers/hid/i2c-hid/i2c-hid-of-goodix.c +++ b/drivers/hid/i2c-hid/i2c-hid-of-goodix.c @@ -27,7 +27,6 @@ struct i2c_hid_of_goodix {

struct regulator *vdd; struct notifier_block nb; - struct mutex regulator_mutex; struct gpio_desc *reset_gpio; const struct goodix_i2c_hid_timing_data *timings; }; @@ -67,8 +66,6 @@ static int ihid_goodix_vdd_notify(struct container_of(nb, struct i2c_hid_of_goodix, nb); int ret = NOTIFY_OK;

- mutex_lock(&ihid_goodix->regulator_mutex); - switch (event) { case REGULATOR_EVENT_PRE_DISABLE: gpiod_set_value_cansleep(ihid_goodix->reset_gpio, 1); @@ -87,8 +84,6 @@ static int ihid_goodix_vdd_notify(struct break; }

- mutex_unlock(&ihid_goodix->regulator_mutex); - return ret; }

@@ -102,8 +97,6 @@ static int i2c_hid_of_goodix_probe(struc if (!ihid_goodix) return -ENOMEM;

- mutex_init(&ihid_goodix->regulator_mutex); - ihid_goodix->ops.power_up = goodix_i2c_hid_power_up; ihid_goodix->ops.power_down = goodix_i2c_hid_power_down;

@@ -130,25 +123,28 @@ static int i2c_hid_of_goodix_probe(struc * long. Holding the controller in reset apparently draws extra * power. */ - mutex_lock(&ihid_goodix->regulator_mutex); ihid_goodix->nb.notifier_call = ihid_goodix_vdd_notify; ret = devm_regulator_register_notifier(ihid_goodix->vdd, &ihid_goodix->nb); - if (ret) { - mutex_unlock(&ihid_goodix->regulator_mutex); + if (ret) return dev_err_probe(&client->dev, ret, "regulator notifier request failed\n"); - }

/* * If someone else is holding the regulator on (or the regulator is * an always-on one) we might never be told to deassert reset. Do it - * now. Here we'll assume that someone else might have _just - * barely_ turned the regulator on so we'll do the full - * "post_power_delay" just in case. + * now... and temporarily bump the regulator reference count just to + * make sure it is impossible for this to race with our own notifier! + * We also assume that someone else might have _just barely_ turned + * the regulator on so we'll do the full "post_power_delay" just in + * case. */ - if (ihid_goodix->reset_gpio && regulator_is_enabled(ihid_goodix->vdd)) + if (ihid_goodix->reset_gpio && regulator_is_enabled(ihid_goodix->vdd)) { + ret = regulator_enable(ihid_goodix->vdd); + if (ret) + return ret; goodix_i2c_hid_deassert_reset(ihid_goodix, true); - mutex_unlock(&ihid_goodix->regulator_mutex); + regulator_disable(ihid_goodix->vdd); + }

return i2c_hid_core_probe(client, &ihid_goodix->ops, 0x0001, 0); }

From: Muhammad Usama Anjum usama.anjum@collabora.com

commit 0316dbb9a017d3231f86e0188376f067ec26a59c upstream.

There is no vmx_pi_mmio_test file. Remove it to get rid of error while creation of selftest archive:

rsync: [sender] link_stat "/kselftest/kvm/x86_64/vmx_pi_mmio_test" failed: No such file or directory (2) rsync error: some files/attrs were not transferred (see previous errors) (code 23) at main.c(1333) [sender=3.2.3]

Fixes: 6a58150859fd ("selftest: KVM: Add intra host migration tests") Reported-by: "kernelci.org bot" bot@kernelci.org Signed-off-by: Muhammad Usama Anjum usama.anjum@collabora.com Message-Id: 20220210172352.1317554-1-usama.anjum@collabora.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/kvm/Makefile | 1 - 1 file changed, 1 deletion(-)

--- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -75,7 +75,6 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test

From: Long Li longli@microsoft.com

commit 3149efcdf2c6314420c418dfc94de53bfd076b1f upstream.

When kernel boots with a NUMA topology with some NUMA nodes offline, the PCI driver should only set an online NUMA node on the device. This can happen during KDUMP where some NUMA nodes are not made online by the KDUMP kernel.

This patch also fixes the case where kernel is booting with "numa=off".

Fixes: 999dd956d838 ("PCI: hv: Add support for protocol 1.3 and support PCI_BUS_RELATIONS2") Signed-off-by: Long Li longli@microsoft.com Reviewed-by: Michael Kelley mikelley@microsoft.com Tested-by: Purna Pavan Chandra Aekkaladevi paekkaladevi@microsoft.com Acked-by: Lorenzo Pieralisi lorenzo.pieralisi@arm.com Link: https://lore.kernel.org/r/1643247814-15184-1-git-send-email-longli@linuxonhy... Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/controller/pci-hyperv.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

--- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1899,8 +1899,17 @@ static void hv_pci_assign_numa_node(stru if (!hv_dev) continue;

- if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY) - set_dev_node(&dev->dev, hv_dev->desc.virtual_numa_node); + if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY && + hv_dev->desc.virtual_numa_node < num_possible_nodes()) + /* + * The kernel may boot with some NUMA nodes offline + * (e.g. in a KDUMP kernel) or with NUMA disabled via + * "numa=off". In those cases, adjust the host provided + * NUMA node to a valid NUMA node used by the kernel. + */ + set_dev_node(&dev->dev, + numa_map_to_online_node( + hv_dev->desc.virtual_numa_node));

put_pcichild(hv_dev); }

From: Alex Henrie alexhenrie24@gmail.com

commit e26a78057c25dd56f112d536319c38735ed92ba4 upstream.

Markus reports that his 2011 MacBook with a German ISO keyboard (USB product code 05ac:0246, HID country code 13) has the tilde key quirk. Seeing as all of the standalone Apple ISO keyboards since about 2008 have the quirk, it seems reasonable to assume that once the integrated laptop keyboards started having the quirk, they likewise never stopped having it.

Reported-by: Markus Wageringel markus.wageringel@gmail.com Signed-off-by: Alex Henrie alexhenrie24@gmail.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/hid-apple.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -580,49 +580,49 @@ static const struct hid_device_id apple_ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ISO), - .driver_data = APPLE_HAS_FN }, + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_ISO), - .driver_data = APPLE_HAS_FN }, + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO), - .driver_data = APPLE_HAS_FN }, + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO), - .driver_data = APPLE_HAS_FN }, + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ISO), - .driver_data = APPLE_HAS_FN }, + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_ISO), - .driver_data = APPLE_HAS_FN }, + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO), - .driver_data = APPLE_HAS_FN }, + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO), - .driver_data = APPLE_HAS_FN }, + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI),

From: Dāvis Mosāns davispuh@gmail.com

commit 2e7be9db125a0bf940c5d65eb5c40d8700f738b5 upstream.

Currently if we get IO error while doing send then we abort without logging information about which file caused issue. So log it to help with debugging.

CC: stable@vger.kernel.org # 4.9+ Signed-off-by: Dāvis Mosāns davispuh@gmail.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/send.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4983,6 +4983,10 @@ static int put_file_data(struct send_ctx lock_page(page); if (!PageUptodate(page)) { unlock_page(page); + btrfs_err(fs_info, + "send: IO error at offset %llu for inode %llu root %llu", + page_offset(page), sctx->cur_ino, + sctx->send_root->root_key.objectid); put_page(page); ret = -EIO; break;

From: Julian Braha julianbraha@gmail.com

[ Upstream commit 579b2c8f72d974f27d85bbd53846f34675ee3b01 ]

When SND_SOC_MT8195_MT6359_RT1011_RT5682 is selected, and GPIOLIB is not selected, Kbuild gives the following warning:

WARNING: unmet direct dependencies detected for SND_SOC_DMIC Depends on [n]: SOUND [=y] && !UML && SND [=y] && SND_SOC [=y] && GPIOLIB [=n] Selected by [y]: - SND_SOC_MT8195_MT6359_RT1011_RT5682 [=y] && SOUND [=y] && !UML && SND [=y] && SND_SOC [=y] && I2C [=y] && SND_SOC_MT8195 [=y] && MTK_PMIC_WRAP [=y]

This is because SND_SOC_MT8195_MT6359_RT1011_RT5682 selects SND_SOC_DMIC without selecting or depending on GPIOLIB, depsite SND_SOC_DMIC depending on GPIOLIB.

This unmet dependency bug was detected by Kismet, a static analysis tool for Kconfig. Please advise if this is not the appropriate solution.

Signed-off-by: Julian Braha julianbraha@gmail.com Reviewed-by: Tzung-Bi Shih tzungbi@google.com Link: https://lore.kernel.org/r/20220117050324.68371-1-julianbraha@gmail.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/mediatek/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig index 3b1ddea26a9ef..76f191ec7bf84 100644 --- a/sound/soc/mediatek/Kconfig +++ b/sound/soc/mediatek/Kconfig @@ -215,7 +215,7 @@ config SND_SOC_MT8195_MT6359_RT1019_RT5682

config SND_SOC_MT8195_MT6359_RT1011_RT5682 tristate "ASoC Audio driver for MT8195 with MT6359 RT1011 RT5682 codec" - depends on I2C + depends on I2C && GPIOLIB depends on SND_SOC_MT8195 && MTK_PMIC_WRAP select SND_SOC_MT6359 select SND_SOC_RT1011

From: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com

[ Upstream commit 17da2d5f93692086dd096a975225ffd5622d0bf8 ]

As reported:

[ 256.104522] ====================================================== [ 256.113783] WARNING: possible circular locking dependency detected [ 256.120093] 5.16.0-rc6-yocto-standard+ #99 Not tainted [ 256.125362] ------------------------------------------------------ [ 256.131673] intel-speed-sel/844 is trying to acquire lock: [ 256.137290] ffffffffc036f0d0 (punit_misc_dev_lock){+.+.}-{3:3}, at: isst_if_open+0x18/0x90 [isst_if_common] [ 256.147171] [ 256.147171] but task is already holding lock: [ 256.153135] ffffffff8ee7cb50 (misc_mtx){+.+.}-{3:3}, at: misc_open+0x2a/0x170 [ 256.160407] [ 256.160407] which lock already depends on the new lock. [ 256.160407] [ 256.168712] [ 256.168712] the existing dependency chain (in reverse order) is: [ 256.176327] [ 256.176327] -> #1 (misc_mtx){+.+.}-{3:3}: [ 256.181946] lock_acquire+0x1e6/0x330 [ 256.186265] __mutex_lock+0x9b/0x9b0 [ 256.190497] mutex_lock_nested+0x1b/0x20 [ 256.195075] misc_register+0x32/0x1a0 [ 256.199390] isst_if_cdev_register+0x65/0x180 [isst_if_common] [ 256.205878] isst_if_probe+0x144/0x16e [isst_if_mmio] ... [ 256.241976] [ 256.241976] -> #0 (punit_misc_dev_lock){+.+.}-{3:3}: [ 256.248552] validate_chain+0xbc6/0x1750 [ 256.253131] __lock_acquire+0x88c/0xc10 [ 256.257618] lock_acquire+0x1e6/0x330 [ 256.261933] __mutex_lock+0x9b/0x9b0 [ 256.266165] mutex_lock_nested+0x1b/0x20 [ 256.270739] isst_if_open+0x18/0x90 [isst_if_common] [ 256.276356] misc_open+0x100/0x170 [ 256.280409] chrdev_open+0xa5/0x1e0 ...

The call sequence suggested that misc_device /dev file can be opened before misc device is yet to be registered, which is done only once.

Here punit_misc_dev_lock was used as common lock, to protect the registration by multiple ISST HW drivers, one time setup, prevent duplicate registry of misc device and prevent load/unload when device is open.

We can split into locks: - One which just prevent duplicate call to misc_register() and one time setup. Also never call again if the misc_register() failed or required one time setup is failed. This lock is not shared with any misc device callbacks.

- The other lock protects registry, load and unload of HW drivers.

Sequence in isst_if_cdev_register() - Register callbacks under punit_misc_dev_open_lock - Call isst_misc_reg() which registers misc_device on the first registry which is under punit_misc_dev_reg_lock, which is not shared with callbacks.

Sequence in isst_if_cdev_unregister Just opposite of isst_if_cdev_register

Reported-and-tested-by: Liwei Song liwei.song@windriver.com Signed-off-by: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com Link: https://lore.kernel.org/r/20220112022521.54669-1-srinivas.pandruvada@linux.i... Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../intel/speed_select_if/isst_if_common.c | 97 ++++++++++++------- 1 file changed, 63 insertions(+), 34 deletions(-)

diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index c9a85eb2e8600..e8424e70d81d2 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -596,7 +596,10 @@ static long isst_if_def_ioctl(struct file *file, unsigned int cmd, return ret; }

-static DEFINE_MUTEX(punit_misc_dev_lock); +/* Lock to prevent module registration when already opened by user space */ +static DEFINE_MUTEX(punit_misc_dev_open_lock); +/* Lock to allow one share misc device for all ISST interace */ +static DEFINE_MUTEX(punit_misc_dev_reg_lock); static int misc_usage_count; static int misc_device_ret; static int misc_device_open; @@ -606,7 +609,7 @@ static int isst_if_open(struct inode *inode, struct file *file) int i, ret = 0;

/* Fail open, if a module is going away */ - mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); for (i = 0; i < ISST_IF_DEV_MAX; ++i) { struct isst_if_cmd_cb *cb = &punit_callbacks[i];

@@ -628,7 +631,7 @@ static int isst_if_open(struct inode *inode, struct file *file) } else { misc_device_open++; } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock);

return ret; } @@ -637,7 +640,7 @@ static int isst_if_relase(struct inode *inode, struct file *f) { int i;

- mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); misc_device_open--; for (i = 0; i < ISST_IF_DEV_MAX; ++i) { struct isst_if_cmd_cb *cb = &punit_callbacks[i]; @@ -645,7 +648,7 @@ static int isst_if_relase(struct inode *inode, struct file *f) if (cb->registered) module_put(cb->owner); } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock);

return 0; } @@ -662,6 +665,43 @@ static struct miscdevice isst_if_char_driver = { .fops = &isst_if_char_driver_ops, };

+static int isst_misc_reg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_device_ret) + goto unlock_exit; + + if (!misc_usage_count) { + misc_device_ret = isst_if_cpu_info_init(); + if (misc_device_ret) + goto unlock_exit; + + misc_device_ret = misc_register(&isst_if_char_driver); + if (misc_device_ret) { + isst_if_cpu_info_exit(); + goto unlock_exit; + } + } + misc_usage_count++; + +unlock_exit: + mutex_unlock(&punit_misc_dev_reg_lock); + + return misc_device_ret; +} + +static void isst_misc_unreg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_usage_count) + misc_usage_count--; + if (!misc_usage_count && !misc_device_ret) { + misc_deregister(&isst_if_char_driver); + isst_if_cpu_info_exit(); + } + mutex_unlock(&punit_misc_dev_reg_lock); +} + /** * isst_if_cdev_register() - Register callback for IOCTL * @device_type: The device type this callback handling. @@ -679,38 +719,31 @@ static struct miscdevice isst_if_char_driver = { */ int isst_if_cdev_register(int device_type, struct isst_if_cmd_cb *cb) { - if (misc_device_ret) - return misc_device_ret; + int ret;

if (device_type >= ISST_IF_DEV_MAX) return -EINVAL;

- mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); + /* Device is already open, we don't want to add new callbacks */ if (misc_device_open) { - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); return -EAGAIN; } - if (!misc_usage_count) { - int ret; - - misc_device_ret = misc_register(&isst_if_char_driver); - if (misc_device_ret) - goto unlock_exit; - - ret = isst_if_cpu_info_init(); - if (ret) { - misc_deregister(&isst_if_char_driver); - misc_device_ret = ret; - goto unlock_exit; - } - } memcpy(&punit_callbacks[device_type], cb, sizeof(*cb)); punit_callbacks[device_type].registered = 1; - misc_usage_count++; -unlock_exit: - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock);

- return misc_device_ret; + ret = isst_misc_reg(); + if (ret) { + /* + * No need of mutex as the misc device register failed + * as no one can open device yet. Hence no contention. + */ + punit_callbacks[device_type].registered = 0; + return ret; + } + return 0; } EXPORT_SYMBOL_GPL(isst_if_cdev_register);

@@ -725,16 +758,12 @@ EXPORT_SYMBOL_GPL(isst_if_cdev_register); */ void isst_if_cdev_unregister(int device_type) { - mutex_lock(&punit_misc_dev_lock); - misc_usage_count--; + isst_misc_unreg(); + mutex_lock(&punit_misc_dev_open_lock); punit_callbacks[device_type].registered = 0; if (device_type == ISST_IF_DEV_MBOX) isst_delete_hash(); - if (!misc_usage_count && !misc_device_ret) { - misc_deregister(&isst_if_char_driver); - isst_if_cpu_info_exit(); - } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); } EXPORT_SYMBOL_GPL(isst_if_cdev_unregister);

From: Michał Winiarski michal.winiarski@intel.com

[ Upstream commit 235528072f28b3b0a1446279b7eaddda36dbf743 ]

Python 3.10.0 contains: 9e09849d20 ("bpo-41006: importlib.util no longer imports typing (GH-20938)")

It causes importlib.util to no longer import importlib.abs, which leads to the following error when trying to use kunit with qemu: AttributeError: module 'importlib' has no attribute 'abc'. Did you mean: '_abc'?

Add the missing import.

Signed-off-by: Michał Winiarski michal.winiarski@intel.com Reviewed-by: Daniel Latypov dlatypov@google.com Reviewed-by: Brendan Higgins brendanhiggins@google.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/kunit/kunit_kernel.py | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 66095568bf327..fae843bf2f0eb 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,6 +6,7 @@ # Author: Felix Guo felixguoxiuping@gmail.com # Author: Brendan Higgins brendanhiggins@google.com

+import importlib.abc import importlib.util import logging import subprocess

From: Li Zhijian lizhijian@cn.fujitsu.com

[ Upstream commit 92d25637a3a45904292c93f1863c6bbda4e3e38f ]

We have some many cases that will create child process as well, such as pidfd_wait. Previously, we will signal/kill the parent process when it is time out, but this signal will not be sent to its child process. In such case, if child process doesn't terminate itself, ksefltest framework will hang forever.

Here we group all its child processes so that kill() can signal all of them in timeout.

Fixed change log: Shuah Khan skhan@linuxfoundation.org

Suggested-by: yang xu xuyang2018.jy@cn.fujitsu.com Signed-off-by: Li Zhijian lizhijian@cn.fujitsu.com Acked-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/kselftest_harness.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 79a182cfa43ad..78e59620d28de 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -875,7 +875,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) }

t->timed_out = true; - kill(t->pid, SIGKILL); + // signal process group + kill(-(t->pid), SIGKILL); }

void __wait_for_test(struct __test_metadata *t) @@ -985,6 +986,7 @@ void __run_test(struct __fixture_metadata *f, ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { + setpgrp(); t->fn(t, variant); if (t->skip) _exit(255);

From: Miquel Raynal miquel.raynal@bootlin.com

[ Upstream commit e5ce576d45bf72fd0e3dc37eff897bfcc488f6a9 ]

Upon error the ieee802154_xmit_complete() helper is not called. Only ieee802154_wake_queue() is called manually. In the Tx case we then leak the skb structure.

Free the skb structure upon error before returning when appropriate.

As the 'is_tx = 0' cannot be moved in the complete handler because of a possible race between the delay in switching to STATE_RX_AACK_ON and a new interrupt, we introduce an intermediate 'was_tx' boolean just for this purpose.

There is no Fixes tag applying here, many changes have been made on this area and the issue kind of always existed.

Suggested-by: Alexander Aring alex.aring@gmail.com Signed-off-by: Miquel Raynal miquel.raynal@bootlin.com Acked-by: Alexander Aring aahringo@redhat.com Link: https://lore.kernel.org/r/20220125121426.848337-4-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt stefan@datenfreihafen.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ieee802154/at86rf230.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 7d67f41387f55..4f5ef8a9a9a87 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -100,6 +100,7 @@ struct at86rf230_local { unsigned long cal_timeout; bool is_tx; bool is_tx_from_off; + bool was_tx; u8 tx_retry; struct sk_buff *tx_skb; struct at86rf230_state_change tx; @@ -343,7 +344,11 @@ at86rf230_async_error_recover_complete(void *context) if (ctx->free) kfree(ctx);

- ieee802154_wake_queue(lp->hw); + if (lp->was_tx) { + lp->was_tx = 0; + dev_kfree_skb_any(lp->tx_skb); + ieee802154_wake_queue(lp->hw); + } }

static void @@ -352,7 +357,11 @@ at86rf230_async_error_recover(void *context) struct at86rf230_state_change *ctx = context; struct at86rf230_local *lp = ctx->lp;

- lp->is_tx = 0; + if (lp->is_tx) { + lp->was_tx = 1; + lp->is_tx = 0; + } + at86rf230_async_state_change(lp, ctx, STATE_RX_AACK_ON, at86rf230_async_error_recover_complete); }

From: Yang Xu xuyang2018.jy@fujitsu.com

[ Upstream commit d18da7ec3719559d6e74937266d0416e6c7e0b31 ]

zram01 uses `free -m` to measure zram memory usage. The results are no sense because they are polluted by all running processes on the system.

We Should only calculate the free memory delta for the current process. So use the third field of /sys/block/zram<id>/mm_stat to measure memory usage instead. The file is available since kernel 4.1.

orig_data_size(first): uncompressed size of data stored in this disk. compr_data_size(second): compressed size of data stored in this disk mem_used_total(third): the amount of memory allocated for this disk

Also remove useless zram cleanup call in zram_fill_fs and so we don't need to cleanup zram twice if fails.

Signed-off-by: Yang Xu xuyang2018.jy@fujitsu.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/zram/zram01.sh | 30 +++++++------------------- 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh index 114863d9fb876..e9e9eb777e2c7 100755 --- a/tools/testing/selftests/zram/zram01.sh +++ b/tools/testing/selftests/zram/zram01.sh @@ -33,8 +33,6 @@ zram_algs="lzo"

zram_fill_fs() { - local mem_free0=$(free -m | awk 'NR==2 {print $4}') - for i in $(seq 0 $(($dev_num - 1))); do echo "fill zram$i..." local b=0 @@ -45,29 +43,17 @@ zram_fill_fs() b=$(($b + 1)) done echo "zram$i can be filled with '$b' KB" - done

- local mem_free1=$(free -m | awk 'NR==2 {print $4}') - local used_mem=$(($mem_free0 - $mem_free1)) + local mem_used_total=`awk '{print $3}' "/sys/block/zram$i/mm_stat"` + local v=$((100 * 1024 * $b / $mem_used_total)) + if [ "$v" -lt 100 ]; then + echo "FAIL compression ratio: 0.$v:1" + ERR_CODE=-1 + return + fi

- local total_size=0 - for sm in $zram_sizes; do - local s=$(echo $sm | sed 's/M//') - total_size=$(($total_size + $s)) + echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" done - - echo "zram used ${used_mem}M, zram disk sizes ${total_size}M" - - local v=$((100 * $total_size / $used_mem)) - - if [ "$v" -lt 100 ]; then - echo "FAIL compression ratio: 0.$v:1" - ERR_CODE=-1 - zram_cleanup - return - fi - - echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" }

check_prereqs

From: Cristian Marussi cristian.marussi@arm.com

[ Upstream commit e051cdf655fa016692008a446a060eff06222bb5 ]

In E_func() macro, on error, print also errno in order to aid debugging.

Cc: Aleksa Sarai cyphar@cyphar.com Signed-off-by: Cristian Marussi cristian.marussi@arm.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/openat2/helpers.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h index a6ea27344db2d..ad5d0ba5b6ce9 100644 --- a/tools/testing/selftests/openat2/helpers.h +++ b/tools/testing/selftests/openat2/helpers.h @@ -62,11 +62,12 @@ bool needs_openat2(const struct open_how *how); (similar to chroot(2)). */ #endif /* RESOLVE_IN_ROOT */

-#define E_func(func, ...) \ - do { \ - if (func(__VA_ARGS__) < 0) \ - ksft_exit_fail_msg("%s:%d %s failed\n", \ - __FILE__, __LINE__, #func);\ +#define E_func(func, ...) \ + do { \ + errno = 0; \ + if (func(__VA_ARGS__) < 0) \ + ksft_exit_fail_msg("%s:%d %s failed - errno:%d\n", \ + __FILE__, __LINE__, #func, errno); \ } while (0)

#define E_asprintf(...) E_func(asprintf, __VA_ARGS__)

From: Cristian Marussi cristian.marussi@arm.com

[ Upstream commit ac9e0a250bb155078601a5b999aab05f2a04d1ab ]

Skip testcases that fail since the requested valid flags combination is not supported by the underlying filesystem.

Cc: Aleksa Sarai cyphar@cyphar.com Signed-off-by: Cristian Marussi cristian.marussi@arm.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/openat2/openat2_test.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c index 1bddbe934204c..7fb902099de45 100644 --- a/tools/testing/selftests/openat2/openat2_test.c +++ b/tools/testing/selftests/openat2/openat2_test.c @@ -259,6 +259,16 @@ void test_openat2_flags(void) unlink(path);

fd = sys_openat2(AT_FDCWD, path, &test->how); + if (fd < 0 && fd == -EOPNOTSUPP) { + /* + * Skip the testcase if it failed because not supported + * by FS. (e.g. a valid O_TMPFILE combination on NFS) + */ + ksft_test_result_skip("openat2 with %s fails with %d (%s)\n", + test->name, fd, strerror(-fd)); + goto next; + } + if (test->err >= 0) failed = (fd < 0); else @@ -303,7 +313,7 @@ void test_openat2_flags(void) else resultfn("openat2 with %s fails with %d (%s)\n", test->name, test->err, strerror(-test->err)); - +next: free(fdpath); fflush(stdout); }

From: Duoming Zhou duoming@zju.edu.cn

[ Upstream commit 4e0f718daf97d47cf7dec122da1be970f145c809 ]

The previous commit 1ade48d0c27d ("ax25: NPD bug when detaching AX25 device") introduce lock_sock() into ax25_kill_by_device to prevent NPD bug. But the concurrency NPD or UAF bug will occur, when lock_sock() or release_sock() dereferences the ax25_cb->sock.

The NULL pointer dereference bug can be shown as below:

ax25_kill_by_device() | ax25_release() | ax25_destroy_socket() | ax25_cb_del() ... | ... | ax25->sk=NULL; lock_sock(s->sk); //(1) | s->ax25_dev = NULL; | ... release_sock(s->sk); //(2) | ... |

The root cause is that the sock is set to null before dereference site (1) or (2). Therefore, this patch extracts the ax25_cb->sock in advance, and uses ax25_list_lock to protect it, which can synchronize with ax25_cb_del() and ensure the value of sock is not null before dereference sites.

The concurrency UAF bug can be shown as below:

ax25_kill_by_device() | ax25_release() | ax25_destroy_socket() ... | ... | sock_put(sk); //FREE lock_sock(s->sk); //(1) | s->ax25_dev = NULL; | ... release_sock(s->sk); //(2) | ... |

The root cause is that the sock is released before dereference site (1) or (2). Therefore, this patch uses sock_hold() to increase the refcount of sock and uses ax25_list_lock to protect it, which can synchronize with ax25_cb_del() in ax25_destroy_socket() and ensure the sock wil not be released before dereference sites.

Signed-off-by: Duoming Zhou duoming@zju.edu.cn Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ax25/af_ax25.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 02f43f3e2c564..44a8730c26acc 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -77,6 +77,7 @@ static void ax25_kill_by_device(struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *s; + struct sock *sk;

if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; @@ -85,13 +86,15 @@ static void ax25_kill_by_device(struct net_device *dev) again: ax25_for_each(s, &ax25_list) { if (s->ax25_dev == ax25_dev) { + sk = s->sk; + sock_hold(sk); spin_unlock_bh(&ax25_list_lock); - lock_sock(s->sk); + lock_sock(sk); s->ax25_dev = NULL; - release_sock(s->sk); + release_sock(sk); ax25_disconnect(s, ENETUNREACH); spin_lock_bh(&ax25_list_lock); - + sock_put(sk); /* The entry could have been deleted from the * list meanwhile and thus the next pointer is * no longer valid. Play it safe and restart

From: Julian Braha julianbraha@gmail.com

[ Upstream commit 3a5286955bf5febc3d151bcb2c5e272e383b64aa ]

When PINCTRL_BCM63XX is selected, and REGMAP is not selected, Kbuild gives the following warning:

WARNING: unmet direct dependencies detected for GPIO_REGMAP Depends on [n]: GPIOLIB [=y] && REGMAP [=n] Selected by [y]: - PINCTRL_BCM63XX [=y] && PINCTRL [=y]

This is because PINCTRL_BCM63XX selects GPIO_REGMAP without selecting or depending on REGMAP, despite GPIO_REGMAP depending on REGMAP.

This unmet dependency bug was detected by Kismet, a static analysis tool for Kconfig. Please advise if this is not the appropriate solution.

Signed-off-by: Julian Braha julianbraha@gmail.com Link: https://lore.kernel.org/r/20220117062557.89568-1-julianbraha@gmail.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/bcm/Kconfig | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/bcm/Kconfig b/drivers/pinctrl/bcm/Kconfig index 8fc1feedd8617..5116b014e2a4f 100644 --- a/drivers/pinctrl/bcm/Kconfig +++ b/drivers/pinctrl/bcm/Kconfig @@ -35,6 +35,7 @@ config PINCTRL_BCM63XX select PINCONF select GENERIC_PINCONF select GPIOLIB + select REGMAP select GPIO_REGMAP

config PINCTRL_BCM6318

From: Darrick J. Wong djwong@kernel.org

[ Upstream commit 5679897eb104cec9e99609c3f045a0c20603da4c ]

Strangely, sync_filesystem ignores the return code from the ->sync_fs call, which means that syscalls like syncfs(2) never see the error. This doesn't seem right, so fix that.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Christoph Hellwig hch@lst.de Acked-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/sync.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/fs/sync.c b/fs/sync.c index 3ce8e2137f310..c7690016453e4 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -29,7 +29,7 @@ */ int sync_filesystem(struct super_block *sb) { - int ret; + int ret = 0;

/* * We need to be protected against the filesystem going from @@ -52,15 +52,21 @@ int sync_filesystem(struct super_block *sb) * at a time. */ writeback_inodes_sb(sb, WB_REASON_SYNC); - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 0); + if (sb->s_op->sync_fs) { + ret = sb->s_op->sync_fs(sb, 0); + if (ret) + return ret; + } ret = sync_blockdev_nowait(sb->s_bdev); - if (ret < 0) + if (ret) return ret;

sync_inodes_sb(sb); - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); + if (sb->s_op->sync_fs) { + ret = sb->s_op->sync_fs(sb, 1); + if (ret) + return ret; + } return sync_blockdev(sb->s_bdev); } EXPORT_SYMBOL(sync_filesystem);

From: Ajish Koshy Ajish.Koshy@microchip.com

[ Upstream commit c26b85ea16365079be8d206b20556a60a0c69ad4 ]

Current code handles completions for SATA devices in mpi_sata_completion() and mpi_sata_event().

However, at the time when any SATA event happens, for almost all the event types, the command is still in the target. It is therefore incorrect to complete the task in sata_event().

There are some events for which we get sata_completions, some need recovery procedure and others abort. All the tasks must be completed via sata_completion() path.

Removed the task done related code from sata_events(). For tasks where we don't get completions, let top layer call abort() to abort the command post timeout.

Link: https://lore.kernel.org/r/20220124082255.86223-1-Ajish.Koshy@microchip.com Acked-by: Jack Wang jinpu.wang@ionos.com Co-developed-by: Viswas G Viswas.G@microchip.com Signed-off-by: Viswas G Viswas.G@microchip.com Signed-off-by: Ajish Koshy Ajish.Koshy@microchip.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/pm8001/pm8001_hwi.c | 18 ------------------ drivers/scsi/pm8001/pm80xx_hwi.c | 26 -------------------------- 2 files changed, 44 deletions(-)

diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 4390c8b9170cd..066290dd57565 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -2695,7 +2695,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, void *piomb) u32 tag = le32_to_cpu(psataPayload->tag); u32 port_id = le32_to_cpu(psataPayload->port_id); u32 dev_id = le32_to_cpu(psataPayload->device_id); - unsigned long flags;

ccb = &pm8001_ha->ccb_info[tag];

@@ -2735,8 +2734,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, void *piomb) ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_DATA_OVERRUN; ts->residual = 0; - if (pm8001_dev) - atomic_dec(&pm8001_dev->running_req); break; case IO_XFER_ERROR_BREAK: pm8001_dbg(pm8001_ha, IO, "IO_XFER_ERROR_BREAK\n"); @@ -2778,7 +2775,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, void *piomb) IO_OPEN_CNX_ERROR_IT_NEXUS_LOSS); ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_QUEUE_FULL; - pm8001_ccb_task_free_done(pm8001_ha, t, ccb, tag); return; } break; @@ -2864,20 +2860,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, void *piomb) ts->stat = SAS_OPEN_TO; break; } - spin_lock_irqsave(&t->task_state_lock, flags); - t->task_state_flags &= ~SAS_TASK_STATE_PENDING; - t->task_state_flags &= ~SAS_TASK_AT_INITIATOR; - t->task_state_flags |= SAS_TASK_STATE_DONE; - if (unlikely((t->task_state_flags & SAS_TASK_STATE_ABORTED))) { - spin_unlock_irqrestore(&t->task_state_lock, flags); - pm8001_dbg(pm8001_ha, FAIL, - "task 0x%p done with io_status 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n", - t, event, ts->resp, ts->stat); - pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); - } else { - spin_unlock_irqrestore(&t->task_state_lock, flags); - pm8001_ccb_task_free_done(pm8001_ha, t, ccb, tag); - } }

/*See the comments for mpi_ssp_completion */ diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 4c5b945bf3187..885bc9e71ff64 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -2828,7 +2828,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, u32 tag = le32_to_cpu(psataPayload->tag); u32 port_id = le32_to_cpu(psataPayload->port_id); u32 dev_id = le32_to_cpu(psataPayload->device_id); - unsigned long flags;

ccb = &pm8001_ha->ccb_info[tag];

@@ -2866,8 +2865,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_DATA_OVERRUN; ts->residual = 0; - if (pm8001_dev) - atomic_dec(&pm8001_dev->running_req); break; case IO_XFER_ERROR_BREAK: pm8001_dbg(pm8001_ha, IO, "IO_XFER_ERROR_BREAK\n"); @@ -2916,11 +2913,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, IO_OPEN_CNX_ERROR_IT_NEXUS_LOSS); ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_QUEUE_FULL; - spin_unlock_irqrestore(&circularQ->oq_lock, - circularQ->lock_flags); - pm8001_ccb_task_free_done(pm8001_ha, t, ccb, tag); - spin_lock_irqsave(&circularQ->oq_lock, - circularQ->lock_flags); return; } break; @@ -3020,24 +3012,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, ts->stat = SAS_OPEN_TO; break; } - spin_lock_irqsave(&t->task_state_lock, flags); - t->task_state_flags &= ~SAS_TASK_STATE_PENDING; - t->task_state_flags &= ~SAS_TASK_AT_INITIATOR; - t->task_state_flags |= SAS_TASK_STATE_DONE; - if (unlikely((t->task_state_flags & SAS_TASK_STATE_ABORTED))) { - spin_unlock_irqrestore(&t->task_state_lock, flags); - pm8001_dbg(pm8001_ha, FAIL, - "task 0x%p done with io_status 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n", - t, event, ts->resp, ts->stat); - pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); - } else { - spin_unlock_irqrestore(&t->task_state_lock, flags); - spin_unlock_irqrestore(&circularQ->oq_lock, - circularQ->lock_flags); - pm8001_ccb_task_free_done(pm8001_ha, t, ccb, tag); - spin_lock_irqsave(&circularQ->oq_lock, - circularQ->lock_flags); - } }

/*See the comments for mpi_ssp_completion */

From: Ming Lei ming.lei@redhat.com

[ Upstream commit edb854a3680bacc9ef9b91ec0c5ff6105886f6f3 ]

We currently use ->cmd_per_lun as initial queue depth for setting up the budget_map. Martin Wilck reported that it is common for the queue_depth to be subsequently updated in slave_configure() based on detected hardware characteristics.

As a result, for some drivers, the static host template settings for cmd_per_lun and can_queue won't actually get used in practice. And if the default values are used to allocate the budget_map, memory may be consumed unnecessarily.

Fix the issue by reallocating the budget_map after ->slave_configure() returns. At that time the device queue_depth should accurately reflect what the hardware needs.

Link: https://lore.kernel.org/r/20220127153733.409132-1-ming.lei@redhat.com Cc: Bart Van Assche bvanassche@acm.org Reported-by: Martin Wilck martin.wilck@suse.com Suggested-by: Martin Wilck martin.wilck@suse.com Tested-by: Martin Wilck mwilck@suse.com Reviewed-by: Martin Wilck mwilck@suse.com Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Ming Lei ming.lei@redhat.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/scsi_scan.c | 55 ++++++++++++++++++++++++++++++++++++---- 1 file changed, 50 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 23e1c0acdeaee..d0ce723299bf7 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -214,6 +214,48 @@ static void scsi_unlock_floptical(struct scsi_device *sdev, SCSI_TIMEOUT, 3, NULL); }

+static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, + unsigned int depth) +{ + int new_shift = sbitmap_calculate_shift(depth); + bool need_alloc = !sdev->budget_map.map; + bool need_free = false; + int ret; + struct sbitmap sb_backup; + + /* + * realloc if new shift is calculated, which is caused by setting + * up one new default queue depth after calling ->slave_configure + */ + if (!need_alloc && new_shift != sdev->budget_map.shift) + need_alloc = need_free = true; + + if (!need_alloc) + return 0; + + /* + * Request queue has to be frozen for reallocating budget map, + * and here disk isn't added yet, so freezing is pretty fast + */ + if (need_free) { + blk_mq_freeze_queue(sdev->request_queue); + sb_backup = sdev->budget_map; + } + ret = sbitmap_init_node(&sdev->budget_map, + scsi_device_max_queue_depth(sdev), + new_shift, GFP_KERNEL, + sdev->request_queue->node, false, true); + if (need_free) { + if (ret) + sdev->budget_map = sb_backup; + else + sbitmap_free(&sb_backup); + ret = 0; + blk_mq_unfreeze_queue(sdev->request_queue); + } + return ret; +} + /** * scsi_alloc_sdev - allocate and setup a scsi_Device * @starget: which target to allocate a &scsi_device for @@ -306,11 +348,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, * default device queue depth to figure out sbitmap shift * since we use this queue depth most of times. */ - if (sbitmap_init_node(&sdev->budget_map, - scsi_device_max_queue_depth(sdev), - sbitmap_calculate_shift(depth), - GFP_KERNEL, sdev->request_queue->node, - false, true)) { + if (scsi_realloc_sdev_budget_map(sdev, depth)) { put_device(&starget->dev); kfree(sdev); goto out; @@ -1017,6 +1055,13 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, } return SCSI_SCAN_NO_RESPONSE; } + + /* + * The queue_depth is often changed in ->slave_configure. + * Set up budget map again since memory consumption of + * the map depends on actual queue depth. + */ + scsi_realloc_sdev_budget_map(sdev, sdev->queue_depth); }

if (sdev->scsi_level >= SCSI_3)

From: John Garry john.garry@huawei.com

[ Upstream commit df7abcaa1246e2537ab4016077b5443bb3c09378 ]

Currently a use-after-free may occur if a sas_task is aborted by the upper layer before we handle the I/O completion in mpi_ssp_completion() or mpi_sata_completion().

In this case, the following are the two steps in handling those I/O completions:

- Call complete() to inform the upper layer handler of completion of the I/O.

- Release driver resources associated with the sas_task in pm8001_ccb_task_free() call.

When complete() is called, the upper layer may free the sas_task. As such, we should not touch the associated sas_task afterwards, but we do so in the pm8001_ccb_task_free() call.

Fix by swapping the complete() and pm8001_ccb_task_free() calls ordering.

Link: https://lore.kernel.org/r/1643289172-165636-4-git-send-email-john.garry@huaw... Reviewed-by: Damien Le Moal damien.lemoal@opensource.wdc.com Acked-by: Jack Wang jinpu.wang@ionos.com Signed-off-by: John Garry john.garry@huawei.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/pm8001/pm80xx_hwi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 885bc9e71ff64..ca4820d99dc70 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -2184,9 +2184,9 @@ mpi_ssp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) pm8001_dbg(pm8001_ha, FAIL, "task 0x%p done with io_status 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n", t, status, ts->resp, ts->stat); + pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); if (t->slow_task) complete(&t->slow_task->completion); - pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); } else { spin_unlock_irqrestore(&t->task_state_lock, flags); pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); @@ -2801,9 +2801,9 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, pm8001_dbg(pm8001_ha, FAIL, "task 0x%p done with io_status 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n", t, status, ts->resp, ts->stat); + pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); if (t->slow_task) complete(&t->slow_task->completion); - pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); } else { spin_unlock_irqrestore(&t->task_state_lock, flags); spin_unlock_irqrestore(&circularQ->oq_lock,

From: Christian Brauner brauner@kernel.org

[ Upstream commit 1a2beb3d5a0b4051067ecf49ea799bee340e0e7c ]

At least one of the addresses will stop functioning after February.

Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- .mailmap | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/.mailmap b/.mailmap index b344067e0acb6..3979fb166e0fd 100644 --- a/.mailmap +++ b/.mailmap @@ -74,6 +74,9 @@ Chris Chiu chris.chiu@canonical.com chiu@endlessos.org Christian Borntraeger borntraeger@linux.ibm.com borntraeger@de.ibm.com Christian Borntraeger borntraeger@linux.ibm.com cborntra@de.ibm.com Christian Borntraeger borntraeger@linux.ibm.com borntrae@de.ibm.com +Christian Brauner brauner@kernel.org christian@brauner.io +Christian Brauner brauner@kernel.org christian.brauner@canonical.com +Christian Brauner brauner@kernel.org christian.brauner@ubuntu.com Christophe Ricard christophe.ricard@gmail.com Christoph Hellwig hch@lst.de Colin Ian King colin.king@intel.com colin.king@canonical.com

From: Sagi Grimberg sagi@grimberg.me

[ Upstream commit ff9fc7ebf5c06de1ef72a69f9b1ab40af8b07f9e ]

While nvme_tcp_submit_async_event_work is checking the ctrl and queue state before preparing the AER command and scheduling io_work, in order to fully prevent a race where this check is not reliable the error recovery work must flush async_event_work before continuing to destroy the admin queue after setting the ctrl state to RESETTING such that there is no race .submit_async_event and the error recovery handler itself changing the ctrl state.

Tested-by: Chris Leech cleech@redhat.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/tcp.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 22046415a0942..891a36d02e7c7 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2104,6 +2104,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl;

nvme_stop_keep_alive(ctrl); + flush_work(&ctrl->async_event_work); nvme_tcp_teardown_io_queues(ctrl, false); /* unquiesce to fail fast pending requests */ nvme_start_queues(ctrl);

From: Steen Hegelund steen.hegelund@microchip.com

[ Upstream commit 81eb8b0b18789e647e65579303529fd52d861cc2 ]

Do not try to use any SKB fields after the packet has been passed up in the receive stack.

Reported-by: kernel test robot lkp@intel.com Reported-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Steen Hegelund steen.hegelund@microchip.com Link: https://lore.kernel.org/r/20220202083039.3774851-1-steen.hegelund@microchip.... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/microchip/sparx5/sparx5_packet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index dc7e5ea6ec158..148d431fcde42 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -145,9 +145,9 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap) skb_put(skb, byte_cnt - ETH_FCS_LEN); eth_skb_pad(skb); skb->protocol = eth_type_trans(skb, netdev); - netif_rx(skb); netdev->stats.rx_bytes += skb->len; netdev->stats.rx_packets++; + netif_rx(skb); }

static int sparx5_inject(struct sparx5 *sparx5,

From: Mario Limonciello mario.limonciello@amd.com

[ Upstream commit 04ef860469fda6a646dc841190d05b31fae68e8c ]

This will cause misconfigured systems to not run the GPU suspend routines.

* In APUs that are properly configured system will go into s2idle. * In APUs that are intended to be S3 but user selects s2idle the GPU will stay fully powered for the suspend. * In APUs that are intended to be s2idle and system misconfigured the GPU will stay fully powered for the suspend. * In systems that are intended to be s2idle, but AMD dGPU is also present, the dGPU will go through S3

Signed-off-by: Mario Limonciello mario.limonciello@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index c811161ce9f09..ab3851c26f71c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2236,6 +2236,7 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) static int amdgpu_pmops_prepare(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev);

/* Return a positive number here so * DPM_FLAG_SMART_SUSPEND works properly @@ -2243,6 +2244,13 @@ static int amdgpu_pmops_prepare(struct device *dev) if (amdgpu_device_supports_boco(drm_dev)) return pm_runtime_suspended(dev);

+ /* if we will not support s3 or s2i for the device + * then skip suspend + */ + if (!amdgpu_acpi_is_s0ix_active(adev) && + !amdgpu_acpi_is_s3_active(adev)) + return 1; + return 0; }

From: Jan Beulich jbeulich@suse.com

[ Upstream commit e25a8d959992f61b64a58fc62fb7951dc6f31d1f ]

This started out with me noticing that "dom0_max_vcpus=<N>" with <N> larger than the number of physical CPUs reported through ACPI tables would not bring up the "excess" vCPU-s. Addressing this is the primary purpose of the change; CPU maps handling is being tidied only as far as is necessary for the change here (with the effect of also avoiding the setting up of too much per-CPU infrastructure, i.e. for CPUs which can never come online).

Noticing that xen_fill_possible_map() is called way too early, whereas xen_filter_cpu_maps() is called too late (after per-CPU areas were already set up), and further observing that each of the functions serves only one of Dom0 or DomU, it looked like it was better to simplify this. Use the .get_smp_config hook instead, uniformly for Dom0 and DomU. xen_fill_possible_map() can be dropped altogether, while xen_filter_cpu_maps() is re-purposed but not otherwise changed.

Signed-off-by: Jan Beulich jbeulich@suse.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Link: https://lore.kernel.org/r/2dbd5f0a-9859-ca2d-085e-a02f7166c610@suse.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/xen/enlighten_pv.c | 4 ---- arch/x86/xen/smp_pv.c | 26 ++++++-------------------- 2 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 5004feb16783d..d47c3d176ae4b 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1341,10 +1341,6 @@ asmlinkage __visible void __init xen_start_kernel(void)

xen_acpi_sleep_register();

- /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; - xen_boot_params_init_edd();

#ifdef CONFIG_ACPI diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 6a8f3b53ab834..4a6019238ee7d 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -148,28 +148,12 @@ int xen_smp_intr_init_pv(unsigned int cpu) return rc; }

-static void __init xen_fill_possible_map(void) -{ - int i, rc; - - if (xen_initial_domain()) - return; - - for (i = 0; i < nr_cpu_ids; i++) { - rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); - if (rc >= 0) { - num_processors++; - set_cpu_possible(i, true); - } - } -} - -static void __init xen_filter_cpu_maps(void) +static void __init _get_smp_config(unsigned int early) { int i, rc; unsigned int subtract = 0;

- if (!xen_initial_domain()) + if (early) return;

num_processors = 0; @@ -210,7 +194,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void) * sure the old memory can be recycled. */ make_lowmem_page_readwrite(xen_initial_gdt);

- xen_filter_cpu_maps(); xen_setup_vcpu_info_placement();

/* @@ -476,5 +459,8 @@ static const struct smp_ops xen_smp_ops __initconst = { void __init xen_smp_init(void) { smp_ops = xen_smp_ops; - xen_fill_possible_map(); + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = _get_smp_config; }

From: Kees Cook keescook@chromium.org

[ Upstream commit dcb85f85fa6f142aae1fe86f399d4503d49f2b60 ]

While the stackleak plugin was already using notrace, objtool is now a bit more picky. Update the notrace uses to noinstr. Silences the following objtool warnings when building with:

CONFIG_DEBUG_ENTRY=y CONFIG_STACK_VALIDATION=y CONFIG_VMLINUX_VALIDATION=y CONFIG_GCC_PLUGIN_STACKLEAK=y

vmlinux.o: warning: objtool: do_syscall_64()+0x9: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x9: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: exc_general_protection()+0x22: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: fixup_bad_iret()+0x20: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: do_machine_check()+0x27: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: .text+0x5346e: call to stackleak_erase() leaves .noinstr.text section vmlinux.o: warning: objtool: .entry.text+0x143: call to stackleak_erase() leaves .noinstr.text section vmlinux.o: warning: objtool: .entry.text+0x10eb: call to stackleak_erase() leaves .noinstr.text section vmlinux.o: warning: objtool: .entry.text+0x17f9: call to stackleak_erase() leaves .noinstr.text section

Note that the plugin's addition of calls to stackleak_track_stack() from noinstr functions is expected to be safe, as it isn't runtime instrumentation and is self-contained.

Cc: Alexander Popov alex.popov@linux.com Suggested-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/stackleak.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/kernel/stackleak.c b/kernel/stackleak.c index ce161a8e8d975..dd07239ddff9f 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -48,7 +48,7 @@ int stack_erasing_sysctl(struct ctl_table *table, int write, #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */

-asmlinkage void notrace stackleak_erase(void) +asmlinkage void noinstr stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ unsigned long kstack_ptr = current->lowest_stack; @@ -102,9 +102,8 @@ asmlinkage void notrace stackleak_erase(void) /* Reset the 'lowest_stack' value for the next syscall */ current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; } -NOKPROBE_SYMBOL(stackleak_erase);

-void __used __no_caller_saved_registers notrace stackleak_track_stack(void) +void __used __no_caller_saved_registers noinstr stackleak_track_stack(void) { unsigned long sp = current_stack_pointer;

From: David Woodhouse dwmw@amazon.co.uk

commit fcb732d8f8cf6084f8480015ad41d25fb023a4dd upstream.

There are circumstances whem kvm_xen_update_runstate_guest() should not sleep because it ends up being called from __schedule() when the vCPU is preempted:

[ 222.830825] kvm_xen_update_runstate_guest+0x24/0x100 [ 222.830878] kvm_arch_vcpu_put+0x14c/0x200 [ 222.830920] kvm_sched_out+0x30/0x40 [ 222.830960] __schedule+0x55c/0x9f0

To handle this, make it use the same trick as __kvm_xen_has_interrupt(), of using the hva from the gfn_to_hva_cache directly. Then it can use pagefault_disable() around the accesses and just bail out if the page is absent (which is unlikely).

I almost switched to using a gfn_to_pfn_cache here and bailing out if kvm_map_gfn() fails, like kvm_steal_time_set_preempted() does — but on closer inspection it looks like kvm_map_gfn() will *always* fail in atomic context for a page in IOMEM, which means it will silently fail to make the update every single time for such guests, AFAICT. So I didn't do it that way after all. And will probably fix that one too.

Cc: stable@vger.kernel.org Fixes: 30b5c851af79 ("KVM: x86/xen: Add support for vCPU runstate information") Signed-off-by: David Woodhouse dwmw@amazon.co.uk Message-Id: b17a93e5ff4561e57b1238e3e7ccd0b613eb827e.camel@infradead.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/xen.c | 97 ++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 67 insertions(+), 30 deletions(-)

--- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -93,32 +93,57 @@ static void kvm_xen_update_runstate(stru void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) { struct kvm_vcpu_xen *vx = &v->arch.xen; + struct gfn_to_hva_cache *ghc = &vx->runstate_cache; + struct kvm_memslots *slots = kvm_memslots(v->kvm); + bool atomic = (state == RUNSTATE_runnable); uint64_t state_entry_time; - unsigned int offset; + int __user *user_state; + uint64_t __user *user_times;

kvm_xen_update_runstate(v, state);

if (!vx->runstate_set) return;

- BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + if (unlikely(slots->generation != ghc->generation || kvm_is_error_hva(ghc->hva)) && + kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len)) + return; + + /* We made sure it fits in a single page */ + BUG_ON(!ghc->memslot); + + if (atomic) + pagefault_disable();

- offset = offsetof(struct compat_vcpu_runstate_info, state_entry_time); -#ifdef CONFIG_X86_64 /* - * The only difference is alignment of uint64_t in 32-bit. - * So the first field 'state' is accessed directly using - * offsetof() (where its offset happens to be zero), while the - * remaining fields which are all uint64_t, start at 'offset' - * which we tweak here by adding 4. + * The only difference between 32-bit and 64-bit versions of the + * runstate struct us the alignment of uint64_t in 32-bit, which + * means that the 64-bit version has an additional 4 bytes of + * padding after the first field 'state'. + * + * So we use 'int __user *user_state' to point to the state field, + * and 'uint64_t __user *user_times' for runstate_entry_time. So + * the actual array of time[] in each state starts at user_times[1]. */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != 0); + BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state) != 0); + user_state = (int __user *)ghc->hva; + + BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct compat_vcpu_runstate_info, + state_entry_time)); +#ifdef CONFIG_X86_64 BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4); BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) != offsetof(struct compat_vcpu_runstate_info, time) + 4);

if (v->kvm->arch.xen.long_mode) - offset = offsetof(struct vcpu_runstate_info, state_entry_time); + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct vcpu_runstate_info, + state_entry_time)); #endif /* * First write the updated state_entry_time at the appropriate @@ -132,10 +157,8 @@ void kvm_xen_update_runstate_guest(struc BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time));

- if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + if (__put_user(state_entry_time, user_times)) + goto out; smp_wmb();

/* @@ -149,11 +172,8 @@ void kvm_xen_update_runstate_guest(struc BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) != sizeof(vx->current_runstate));

- if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->current_runstate, - offsetof(struct vcpu_runstate_info, state), - sizeof(vx->current_runstate))) - return; + if (__put_user(vx->current_runstate, user_state)) + goto out;

/* * Write the actual runstate times immediately after the @@ -168,24 +188,23 @@ void kvm_xen_update_runstate_guest(struc BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof(vx->runstate_times));

- if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->runstate_times[0], - offset + sizeof(u64), - sizeof(vx->runstate_times))) - return; - + if (__copy_to_user(user_times + 1, vx->runstate_times, sizeof(vx->runstate_times))) + goto out; smp_wmb();

/* * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's * runstate_entry_time field. */ - state_entry_time &= ~XEN_RUNSTATE_UPDATE; - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + __put_user(state_entry_time, user_times); + smp_wmb(); + + out: + mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + + if (atomic) + pagefault_enable(); }

int __kvm_xen_has_interrupt(struct kvm_vcpu *v) @@ -337,6 +356,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcp break; }

+ /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache, data->u.gpa, @@ -354,6 +379,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcp break; }

+ /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct pvclock_vcpu_time_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache, data->u.gpa, @@ -375,6 +406,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcp break; }

+ /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_runstate_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.runstate_cache, data->u.gpa,

From: Maxim Levitsky mlevitsk@redhat.com

commit c53bbe2145f51d3bc0438c2db02e737b9b598bf3 upstream.

When the guest doesn't enable paging, and NPT/EPT is disabled, we use guest't paging CR3's as KVM's shadow paging pointer and we are technically in direct mode as if we were to use NPT/EPT.

In direct mode we create SPTEs with user mode permissions because usually in the direct mode the NPT/EPT doesn't need to restrict access based on guest CPL (there are MBE/GMET extenstions for that but KVM doesn't use them).

In this special "use guest paging as direct" mode however, and if CR4.SMAP/CR4.SMEP are enabled, that will make the CPU fault on each access and KVM will enter endless loop of page faults.

Since page protection doesn't have any meaning in !PG case, just don't passthrough these bits.

The fix is the same as was done for VMX in commit: commit 656ec4a4928a ("KVM: VMX: fix SMEP and SMAP without EPT")

This fixes the boot of windows 10 without NPT for good. (Without this patch, BSP boots, but APs were stuck in endless loop of page faults, causing the VM boot with 1 CPU)

Signed-off-by: Maxim Levitsky mlevitsk@redhat.com Cc: stable@vger.kernel.org Message-Id: 20220207155447.840194-2-mlevitsk@redhat.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/svm/svm.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

--- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1795,6 +1795,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, { struct vcpu_svm *svm = to_svm(vcpu); u64 hcr0 = cr0; + bool old_paging = is_paging(vcpu);

#ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { @@ -1811,8 +1812,11 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, #endif vcpu->arch.cr0 = cr0;

- if (!npt_enabled) + if (!npt_enabled) { hcr0 |= X86_CR0_PG | X86_CR0_WP; + if (old_paging != is_paging(vcpu)) + svm_set_cr4(vcpu, kvm_read_cr4(vcpu)); + }

/* * re-enable caching here because the QEMU bios @@ -1856,8 +1860,12 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, svm_flush_tlb(vcpu);

vcpu->arch.cr4 = cr4; - if (!npt_enabled) + if (!npt_enabled) { cr4 |= X86_CR4_PAE; + + if (!is_paging(vcpu)) + cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); + } cr4 |= host_cr4_mce; to_svm(vcpu)->vmcb->save.cr4 = cr4; vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);

From: Maxim Levitsky mlevitsk@redhat.com

commit e8efa4ff00374d2e6f47f6e4628ca3b541c001af upstream.

While usually, restoring the smm state makes the KVM enter the nested guest thus a different vmcb (vmcb02 vs vmcb01), KVM should still mark it as dirty, since hardware can in theory cache multiple vmcbs.

Failure to do so, combined with lack of setting the nested_run_pending (which is fixed in the next patch), might make KVM re-enter vmcb01, which was just exited from, with completely different set of guest state registers (SMM vs non SMM) and without proper dirty bits set, which results in the CPU reusing stale IDTR pointer which leads to a guest shutdown on any interrupt.

On the real hardware this usually doesn't happen, but when running nested, L0's KVM does check and honour few dirty bits, causing this issue to happen.

This patch fixes boot of hyperv and SMM enabled windows VM running nested on KVM.

Signed-off-by: Maxim Levitsky mlevitsk@redhat.com Cc: stable@vger.kernel.org Message-Id: 20220207155447.840194-4-mlevitsk@redhat.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/svm/svm.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4449,6 +4449,8 @@ static int svm_leave_smm(struct kvm_vcpu * Enter the nested guest now */

+ vmcb_mark_all_dirty(svm->vmcb01.ptr); + vmcb12 = map.hva; nested_load_control_from_vmcb12(svm, &vmcb12->control); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);

From: Johannes Berg johannes.berg@intel.com

commit bea2662e7818e15d7607d17d57912ac984275d94 upstream.

If no firmware was present at all (or, presumably, all of the firmware files failed to parse), we end up unbinding by calling device_release_driver(), which calls remove(), which then in iwlwifi calls iwl_drv_stop(), freeing the 'drv' struct. However the new code I added will still erroneously access it after it was freed.

Set 'failure=false' in this case to avoid the access, all data was already freed anyway.

Cc: stable@vger.kernel.org Reported-by: Stefan Agner stefan@agner.ch Reported-by: Wolfgang Walter linux@stwm.de Reported-by: Jason Self jason@bluehome.net Reported-by: Dominik Behr dominik@dominikbehr.com Reported-by: Marek Marczykowski-Górecki marmarek@invisiblethingslab.com Fixes: ab07506b0454 ("iwlwifi: fix leaks/bad data after failed firmware load") Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/20220208114728.e6b514cf4c85.Iffb575ca2a623d7859b54... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1656,6 +1656,8 @@ static void iwl_req_fw_callback(const st out_unbind: complete(&drv->request_firmware_complete); device_release_driver(drv->trans->dev); + /* drv has just been freed by the release */ + failure = false; free: if (failure) iwl_dealloc_ucode(drv);

From: Nicholas Bishop nicholasbishop@google.com

commit 364438fd629f7611a84c8e6d7de91659300f1502 upstream.

The iMac 12,1 does not use the gmux driver for backlight, so the radeon backlight device is needed to set the brightness.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1838 Signed-off-by: Nicholas Bishop nicholasbishop@google.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/radeon/atombios_encoders.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -198,7 +198,8 @@ void radeon_atom_backlight_init(struct r * so don't register a backlight device */ if ((rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) && - (rdev->pdev->device == 0x6741)) + (rdev->pdev->device == 0x6741) && + !dmi_match(DMI_PRODUCT_NAME, "iMac12,1")) return;

if (!radeon_encoder->enc_priv)

From: Yifan Zhang yifan1.zhang@amd.com

commit 9c4f59ea3f865693150edf0c91d1cc6b451360dd upstream.

the 2nd parameter should be smu msg type rather than asic msg index.

Fixes: 7d38d9dc4ecc ("drm/amdgpu: add mode2 reset support for yellow carp") Signed-off-by: Yifan Zhang yifan1.zhang@amd.com Acked-by: Aaron Liu aaron.liu@amd.com Reviewed-by: Huang Rui ray.huang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-)

--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -282,14 +282,9 @@ static int yellow_carp_post_smu_init(str

static int yellow_carp_mode_reset(struct smu_context *smu, int type) { - int ret = 0, index = 0; + int ret = 0;

- index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG, - SMU_MSG_GfxDeviceDriverReset); - if (index < 0) - return index == -EACCES ? 0 : index; - - ret = smu_cmn_send_smc_msg_with_param(smu, (uint16_t)index, type, NULL); + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, type, NULL); if (ret) dev_err(smu->adev->dev, "Failed to mode reset!\n");

From: Jani Nikula jani.nikula@intel.com

commit ea958422291de248b9e2eaaeea36004e84b64043 upstream.

The mapping from enum port to whatever port numbering scheme is used by the SWSCI Display Power State Notification is odd, and the memory of it has faded. In any case, the parameter only has space for ports numbered [0..4], and UBSAN reports bit shift beyond it when the platform has port F or more.

Since the SWSCI functionality is supposed to be obsolete for new platforms (i.e. ones that might have port F or more), just bail out early if the mapped and mangled port number is beyond what the Display Power State Notification can support.

Fixes: 9c4b0a683193 ("drm/i915: add opregion function to notify bios of encoder enable/disable") Cc: stable@vger.kernel.org # v3.13+ Cc: Ville Syrjälä ville.syrjala@linux.intel.com Cc: Lucas De Marchi lucas.demarchi@intel.com Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/4800 Signed-off-by: Jani Nikula jani.nikula@intel.com Reviewed-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/cc363f42d6b5a5932b6d218fefcc8b... (cherry picked from commit 24a644ebbfd3b13cda702f98907f9dd123e34bf9) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_opregion.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)

--- a/drivers/gpu/drm/i915/display/intel_opregion.c +++ b/drivers/gpu/drm/i915/display/intel_opregion.c @@ -360,6 +360,21 @@ int intel_opregion_notify_encoder(struct port++; }

+ /* + * The port numbering and mapping here is bizarre. The now-obsolete + * swsci spec supports ports numbered [0..4]. Port E is handled as a + * special case, but port F and beyond are not. The functionality is + * supposed to be obsolete for new platforms. Just bail out if the port + * number is out of bounds after mapping. + */ + if (port > 4) { + drm_dbg_kms(&dev_priv->drm, + "[ENCODER:%d:%s] port %c (index %u) out of bounds for display power state notification\n", + intel_encoder->base.base.id, intel_encoder->base.name, + port_name(intel_encoder->port), port); + return -EINVAL; + } + if (!enable) parm |= 4 << 8;

From: Ville Syrjälä ville.syrjala@linux.intel.com

commit 8d9d2a723d64b650f2e6423024ccb4a33f0cdc40 upstream.

The bogus loop from compute_dbuf_slices() was copied into check_mbus_joined() as well. So this lookup is wrong as well. Fix it.

Cc: stable@vger.kernel.org Fixes: f4dc00863226 ("drm/i915/adl_p: MBUS programming") Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20220207132700.481-2-ville.syr... Reviewed-by: Jani Nikula jani.nikula@intel.com (cherry picked from commit 053f2b85631316a9226f6340c1c0fd95634f7a5b) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/intel_pm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4843,7 +4843,7 @@ static bool check_mbus_joined(u8 active_ { int i;

- for (i = 0; i < dbuf_slices[i].active_pipes; i++) { + for (i = 0; dbuf_slices[i].active_pipes != 0; i++) { if (dbuf_slices[i].active_pipes == active_pipes) return dbuf_slices[i].join_mbus; }

From: Jens Wiklander jens.wiklander@linaro.org

[ Upstream commit 1e2c3ef0496e72ba9001da5fd1b7ed56ccb30597 ]

Exports the two functions teedev_open() and teedev_close_context() in order to make it easier to create a driver internal struct tee_context.

Reviewed-by: Sumit Garg sumit.garg@linaro.org Signed-off-by: Jens Wiklander jens.wiklander@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/tee/tee_core.c | 6 ++++-- include/linux/tee_drv.h | 14 ++++++++++++++ 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 85102d12d7169..3fc426dad2df3 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -43,7 +43,7 @@ static DEFINE_SPINLOCK(driver_lock); static struct class *tee_class; static dev_t tee_devt;

-static struct tee_context *teedev_open(struct tee_device *teedev) +struct tee_context *teedev_open(struct tee_device *teedev) { int rc; struct tee_context *ctx; @@ -70,6 +70,7 @@ static struct tee_context *teedev_open(struct tee_device *teedev) return ERR_PTR(rc);

} +EXPORT_SYMBOL_GPL(teedev_open);

void teedev_ctx_get(struct tee_context *ctx) { @@ -96,13 +97,14 @@ void teedev_ctx_put(struct tee_context *ctx) kref_put(&ctx->refcount, teedev_ctx_release); }

-static void teedev_close_context(struct tee_context *ctx) +void teedev_close_context(struct tee_context *ctx) { struct tee_device *teedev = ctx->teedev;

teedev_ctx_put(ctx); tee_device_put(teedev); } +EXPORT_SYMBOL_GPL(teedev_close_context);

static int tee_open(struct inode *inode, struct file *filp) { diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index cf5999626e28d..5e1533ee3785b 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -587,4 +587,18 @@ struct tee_client_driver { #define to_tee_client_driver(d) \ container_of(d, struct tee_client_driver, driver)

+/** + * teedev_open() - Open a struct tee_device + * @teedev: Device to open + * + * @return a pointer to struct tee_context on success or an ERR_PTR on failure. + */ +struct tee_context *teedev_open(struct tee_device *teedev); + +/** + * teedev_close_context() - closes a struct tee_context + * @ctx: The struct tee_context to close + */ +void teedev_close_context(struct tee_context *ctx); + #endif /*__TEE_DRV_H*/

From: Robin Murphy robin.murphy@arm.com

commit 59f39bfa6553d598cb22f694d45e89547f420d85 upstream.

drm_gem_cma_mmap() cannot assume every implementation of dma_mmap_wc() will end up calling remap_pfn_range() (which happens to set the relevant vma flag, among others), so in order to make sure expectations around VM_DONTEXPAND are met, let it explicitly set the flag like most other GEM mmap implementations do.

This avoids repeated warnings on a small minority of systems where the display is behind an IOMMU, and has a simple driver which does not override drm_gem_cma_default_funcs. Arm hdlcd is an in-tree affected driver. Out-of-tree, the Apple DCP driver is affected; this fix is required for DCP to be mainlined.

[Alyssa: Update commit message.]

Fixes: c40069cb7bd6 ("drm: add mmap() to drm_gem_object_funcs") Acked-by: Daniel Vetter daniel@ffwll.ch Signed-off-by: Robin Murphy robin.murphy@arm.com Signed-off-by: Alyssa Rosenzweig alyssa.rosenzweig@collabora.com Link: https://patchwork.freedesktop.org/patch/msgid/20211013143654.39031-1-alyssa@... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/drm_gem_cma_helper.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -518,6 +518,7 @@ int drm_gem_cma_mmap(struct drm_gem_obje */ vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node); vma->vm_flags &= ~VM_PFNMAP; + vma->vm_flags |= VM_DONTEXPAND;

cma_obj = to_drm_gem_cma_obj(obj);

From: Matthew Auld matthew.auld@intel.com

commit 0bdc0a0699929c814a8aecd55d2accb8c11beae2 upstream.

For some reason we are selecting PRIO_HAS_PAGES when we don't have mm.pages, and vice versa.

v2(Thomas): - Add missing fixes tag

Fixes: 213d50927763 ("drm/i915/ttm: Introduce a TTM i915 gem object backend") Signed-off-by: Matthew Auld matthew.auld@intel.com Cc: Thomas Hellström thomas.hellstrom@linux.intel.com Reviewed-by: Thomas Hellström thomas.hellstrom@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20220209111652.468762-1-matthe... (cherry picked from commit ba2c5d15022a565da187d90e2fe44768e33e5034) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -787,11 +787,9 @@ static void i915_ttm_adjust_lru(struct d if (obj->mm.madv != I915_MADV_WILLNEED) { bo->priority = I915_TTM_PRIO_PURGE; } else if (!i915_gem_object_has_pages(obj)) { - if (bo->priority < I915_TTM_PRIO_HAS_PAGES) - bo->priority = I915_TTM_PRIO_HAS_PAGES; + bo->priority = I915_TTM_PRIO_NO_PAGES; } else { - if (bo->priority > I915_TTM_PRIO_NO_PAGES) - bo->priority = I915_TTM_PRIO_NO_PAGES; + bo->priority = I915_TTM_PRIO_HAS_PAGES; }

ttm_bo_move_to_lru_tail(bo, bo->resource, NULL);

From: Johannes Berg johannes.berg@intel.com

commit 4c29c1e27a1e178a219b3877d055e6dd643bdfda upstream.

If we run into this error path, we shouldn't unlock the mutex since it's not locked since. Fix this in the gen2 code as well.

Fixes: eda50cde58de ("iwlwifi: pcie: add context information support") Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/iwlwifi.20220128142706.b8b0dfce16ef.Ie20f0f7b23e59... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -384,8 +384,7 @@ int iwl_trans_pcie_gen2_start_fw(struct /* This may fail if AMT took ownership of the device */ if (iwl_pcie_prepare_card_hw(trans)) { IWL_WARN(trans, "Exit HW not ready\n"); - ret = -EIO; - goto out; + return -EIO; }

iwl_enable_rfkill_int(trans);

From: Miri Korenblit miriam.rachel.korenblit@intel.com

commit 973f02c932b0be41a26bb9bdf38b7b92721611d2 upstream.

There are a couple of bugs in this function:

1. It is declared as a non-static function, even though it's only used in one file. 2. Its return value should be of type u32 but it returns (in some cases) -1.

Fix them by making this function static and returning an error value of type unsigned.

In addition, we're assigning the return value of this function as the legacy rate even if the function returned an error value. Fix this by assigning the lowest rate in this case.

Signed-off-by: Miri Korenblit miriam.rachel.korenblit@intel.com Reported-by: Ye Guojin ye.guojin@zte.com.cn Reported-by: Zeal Robot zealci@zte.com.cn Fixes: 9998f81e4ba5 ("iwlwifi: mvm: convert old rate & flags to the new format.") Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/iwlwifi.20220128142706.5612eeb9d6d0.I992e10d93fc22... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/intel/iwlwifi/fw/api/rs.h | 1 drivers/net/wireless/intel/iwlwifi/fw/rs.c | 33 +++++++++++++------------ 2 files changed, 18 insertions(+), 16 deletions(-)

--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h @@ -710,7 +710,6 @@ struct iwl_lq_cmd {

u8 iwl_fw_rate_idx_to_plcp(int idx); u32 iwl_new_rate_from_v1(u32 rate_v1); -u32 iwl_legacy_rate_to_fw_idx(u32 rate_n_flags); const struct iwl_rate_mcs_info *iwl_rate_mcs(int idx); const char *iwl_rs_pretty_ant(u8 ant); const char *iwl_rs_pretty_bw(int bw); --- a/drivers/net/wireless/intel/iwlwifi/fw/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/rs.c @@ -91,6 +91,20 @@ const char *iwl_rs_pretty_bw(int bw) } IWL_EXPORT_SYMBOL(iwl_rs_pretty_bw);

+static u32 iwl_legacy_rate_to_fw_idx(u32 rate_n_flags) +{ + int rate = rate_n_flags & RATE_LEGACY_RATE_MSK_V1; + int idx; + bool ofdm = !(rate_n_flags & RATE_MCS_CCK_MSK_V1); + int offset = ofdm ? IWL_FIRST_OFDM_RATE : 0; + int last = ofdm ? IWL_RATE_COUNT_LEGACY : IWL_FIRST_OFDM_RATE; + + for (idx = offset; idx < last; idx++) + if (iwl_fw_rate_idx_to_plcp(idx) == rate) + return idx - offset; + return IWL_RATE_INVALID; +} + u32 iwl_new_rate_from_v1(u32 rate_v1) { u32 rate_v2 = 0; @@ -144,7 +158,10 @@ u32 iwl_new_rate_from_v1(u32 rate_v1) } else { u32 legacy_rate = iwl_legacy_rate_to_fw_idx(rate_v1);

- WARN_ON(legacy_rate < 0); + if (WARN_ON_ONCE(legacy_rate == IWL_RATE_INVALID)) + legacy_rate = (rate_v1 & RATE_MCS_CCK_MSK_V1) ? + IWL_FIRST_CCK_RATE : IWL_FIRST_OFDM_RATE; + rate_v2 |= legacy_rate; if (!(rate_v1 & RATE_MCS_CCK_MSK_V1)) rate_v2 |= RATE_MCS_LEGACY_OFDM_MSK; @@ -172,20 +189,6 @@ u32 iwl_new_rate_from_v1(u32 rate_v1) } IWL_EXPORT_SYMBOL(iwl_new_rate_from_v1);

-u32 iwl_legacy_rate_to_fw_idx(u32 rate_n_flags) -{ - int rate = rate_n_flags & RATE_LEGACY_RATE_MSK_V1; - int idx; - bool ofdm = !(rate_n_flags & RATE_MCS_CCK_MSK_V1); - int offset = ofdm ? IWL_FIRST_OFDM_RATE : 0; - int last = ofdm ? IWL_RATE_COUNT_LEGACY : IWL_FIRST_OFDM_RATE; - - for (idx = offset; idx < last; idx++) - if (iwl_fw_rate_idx_to_plcp(idx) == rate) - return idx - offset; - return -1; -} - int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate) { char *type;

From: Eric Dumazet edumazet@google.com

commit 75063c9294fb239bbe64eb72141b6871fe526d29 upstream.

Calling nf_defrag_ipv4_disable() instead of nf_defrag_ipv6_disable() was probably not the intent.

I found this by code inspection, while chasing a possible issue in TPROXY.

Fixes: de8c12110a13 ("netfilter: disable defrag once its no longer needed") Signed-off-by: Eric Dumazet edumazet@google.com Reviewed-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netfilter/xt_socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -221,7 +221,7 @@ static void socket_mt_destroy(const stru if (par->family == NFPROTO_IPV4) nf_defrag_ipv4_disable(par->net); else if (par->family == NFPROTO_IPV6) - nf_defrag_ipv4_disable(par->net); + nf_defrag_ipv6_disable(par->net); }

static struct xt_match socket_mt_reg[] __read_mostly = {

From: Pablo Neira Ayuso pablo@netfilter.org

commit 2b4e5fb4d3776c391e40fb33673ba946dd96012d upstream.

Disable the IPv4 hooks if the IPv6 hooks fail to be registered.

Fixes: ad49d86e07a4 ("netfilter: nf_tables: Add synproxy support") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netfilter/nft_synproxy.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -191,8 +191,10 @@ static int nft_synproxy_do_init(const st if (err) goto nf_ct_failure; err = nf_synproxy_ipv6_init(snet, ctx->net); - if (err) + if (err) { + nf_synproxy_ipv4_fini(snet, ctx->net); goto nf_ct_failure; + } break; }

From: Eric Dumazet edumazet@google.com

commit 9fcf986cc4bc6a3a39f23fbcbbc3a9e52d3c24fd upstream.

fib_alias_hw_flags_set() can be used by concurrent threads, and is only RCU protected.

We need to annotate accesses to following fields of struct fib_alias:

offload, trap, offload_failed

Because of READ_ONCE()WRITE_ONCE() limitations, make these field u8.

BUG: KCSAN: data-race in fib_alias_hw_flags_set / fib_alias_hw_flags_set

read to 0xffff888134224a6a of 1 bytes by task 2013 on cpu 1: fib_alias_hw_flags_set+0x28a/0x470 net/ipv4/fib_trie.c:1050 nsim_fib4_rt_hw_flags_set drivers/net/netdevsim/fib.c:350 [inline] nsim_fib4_rt_add drivers/net/netdevsim/fib.c:367 [inline] nsim_fib4_rt_insert drivers/net/netdevsim/fib.c:429 [inline] nsim_fib4_event drivers/net/netdevsim/fib.c:461 [inline] nsim_fib_event drivers/net/netdevsim/fib.c:881 [inline] nsim_fib_event_work+0x1852/0x2cf0 drivers/net/netdevsim/fib.c:1477 process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 process_scheduled_works kernel/workqueue.c:2370 [inline] worker_thread+0x7df/0xa70 kernel/workqueue.c:2456 kthread+0x1bf/0x1e0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30

write to 0xffff888134224a6a of 1 bytes by task 4872 on cpu 0: fib_alias_hw_flags_set+0x2d5/0x470 net/ipv4/fib_trie.c:1054 nsim_fib4_rt_hw_flags_set drivers/net/netdevsim/fib.c:350 [inline] nsim_fib4_rt_add drivers/net/netdevsim/fib.c:367 [inline] nsim_fib4_rt_insert drivers/net/netdevsim/fib.c:429 [inline] nsim_fib4_event drivers/net/netdevsim/fib.c:461 [inline] nsim_fib_event drivers/net/netdevsim/fib.c:881 [inline] nsim_fib_event_work+0x1852/0x2cf0 drivers/net/netdevsim/fib.c:1477 process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 process_scheduled_works kernel/workqueue.c:2370 [inline] worker_thread+0x7df/0xa70 kernel/workqueue.c:2456 kthread+0x1bf/0x1e0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30

value changed: 0x00 -> 0x02

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 4872 Comm: kworker/0:0 Not tainted 5.17.0-rc3-syzkaller-00188-g1d41d2e82623-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events nsim_fib_event_work

Fixes: 90b93f1b31f8 ("ipv4: Add "offload" and "trap" indications to routes") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Reviewed-by: Ido Schimmel idosch@nvidia.com Link: https://lore.kernel.org/r/20220216173217.3792411-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/fib_lookup.h | 7 +++---- net/ipv4/fib_semantics.c | 6 +++--- net/ipv4/fib_trie.c | 22 +++++++++++++--------- net/ipv4/route.c | 4 ++-- 4 files changed, 21 insertions(+), 18 deletions(-)

--- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -16,10 +16,9 @@ struct fib_alias { u8 fa_slen; u32 tb_id; s16 fa_default; - u8 offload:1, - trap:1, - offload_failed:1, - unused:5; + u8 offload; + u8 trap; + u8 offload_failed; struct rcu_head rcu; };

--- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -524,9 +524,9 @@ void rtmsg_fib(int event, __be32 key, st fri.dst_len = dst_len; fri.tos = fa->fa_tos; fri.type = fa->fa_type; - fri.offload = fa->offload; - fri.trap = fa->trap; - fri.offload_failed = fa->offload_failed; + fri.offload = READ_ONCE(fa->offload); + fri.trap = READ_ONCE(fa->trap); + fri.offload_failed = READ_ONCE(fa->offload_failed); err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1047,19 +1047,23 @@ void fib_alias_hw_flags_set(struct net * if (!fa_match) goto out;

- if (fa_match->offload == fri->offload && fa_match->trap == fri->trap && - fa_match->offload_failed == fri->offload_failed) + /* These are paired with the WRITE_ONCE() happening in this function. + * The reason is that we are only protected by RCU at this point. + */ + if (READ_ONCE(fa_match->offload) == fri->offload && + READ_ONCE(fa_match->trap) == fri->trap && + READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out;

- fa_match->offload = fri->offload; - fa_match->trap = fri->trap; + WRITE_ONCE(fa_match->offload, fri->offload); + WRITE_ONCE(fa_match->trap, fri->trap);

/* 2 means send notifications only if offload_failed was changed. */ if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 && - fa_match->offload_failed == fri->offload_failed) + READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out;

- fa_match->offload_failed = fri->offload_failed; + WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);

if (!net->ipv4.sysctl_fib_notify_on_flag_change) goto out; @@ -2297,9 +2301,9 @@ static int fn_trie_dump_leaf(struct key_ fri.dst_len = KEYLENGTH - fa->fa_slen; fri.tos = fa->fa_tos; fri.type = fa->fa_type; - fri.offload = fa->offload; - fri.trap = fa->trap; - fri.offload_failed = fa->offload_failed; + fri.offload = READ_ONCE(fa->offload); + fri.trap = READ_ONCE(fa->trap); + fri.offload_failed = READ_ONCE(fa->offload_failed); err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3393,8 +3393,8 @@ static int inet_rtm_getroute(struct sk_b fa->fa_tos == fri.tos && fa->fa_info == res.fi && fa->fa_type == fri.type) { - fri.offload = fa->offload; - fri.trap = fa->trap; + fri.offload = READ_ONCE(fa->offload); + fri.trap = READ_ONCE(fa->trap); break; } }

From: Ignat Korchagin ignat@cloudflare.com

commit 26394fc118d6115390bd5b3a0fb17096271da227 upstream.

Some time ago 8965779d2c0e ("ipv6,mcast: always hold idev->lock before mca_lock") switched ipv6_get_lladdr() to __ipv6_get_lladdr(), which is rcu-unsafe version. That was OK, because idev->lock was held for these codepaths.

In 88e2ca308094 ("mld: convert ifmcaddr6 to RCU") these external locks were removed, so we probably need to restore the original rcu-safe call.

Otherwise, we occasionally get a machine crashed/stalled with the following in dmesg:

[ 3405.966610][T230589] general protection fault, probably for non-canonical address 0xdead00000000008c: 0000 [#1] SMP NOPTI [ 3405.982083][T230589] CPU: 44 PID: 230589 Comm: kworker/44:3 Tainted: G O 5.15.19-cloudflare-2022.2.1 #1 [ 3405.998061][T230589] Hardware name: SUPA-COOL-SERV [ 3406.009552][T230589] Workqueue: mld mld_ifc_work [ 3406.017224][T230589] RIP: 0010:__ipv6_get_lladdr+0x34/0x60 [ 3406.025780][T230589] Code: 57 10 48 83 c7 08 48 89 e5 48 39 d7 74 3e 48 8d 82 38 ff ff ff eb 13 48 8b 90 d0 00 00 00 48 8d 82 38 ff ff ff 48 39 d7 74 22 <66> 83 78 32 20 77 1b 75 e4 89 ca 23 50 2c 75 dd 48 8b 50 08 48 8b [ 3406.055748][T230589] RSP: 0018:ffff94e4b3fc3d10 EFLAGS: 00010202 [ 3406.065617][T230589] RAX: dead00000000005a RBX: ffff94e4b3fc3d30 RCX: 0000000000000040 [ 3406.077477][T230589] RDX: dead000000000122 RSI: ffff94e4b3fc3d30 RDI: ffff8c3a31431008 [ 3406.089389][T230589] RBP: ffff94e4b3fc3d10 R08: 0000000000000000 R09: 0000000000000000 [ 3406.101445][T230589] R10: ffff8c3a31430000 R11: 000000000000000b R12: ffff8c2c37887100 [ 3406.113553][T230589] R13: ffff8c3a39537000 R14: 00000000000005dc R15: ffff8c3a31431000 [ 3406.125730][T230589] FS: 0000000000000000(0000) GS:ffff8c3b9fc80000(0000) knlGS:0000000000000000 [ 3406.138992][T230589] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3406.149895][T230589] CR2: 00007f0dfea1db60 CR3: 000000387b5f2000 CR4: 0000000000350ee0 [ 3406.162421][T230589] Call Trace: [ 3406.170235][T230589] <TASK> [ 3406.177736][T230589] mld_newpack+0xfe/0x1a0 [ 3406.186686][T230589] add_grhead+0x87/0xa0 [ 3406.195498][T230589] add_grec+0x485/0x4e0 [ 3406.204310][T230589] ? newidle_balance+0x126/0x3f0 [ 3406.214024][T230589] mld_ifc_work+0x15d/0x450 [ 3406.223279][T230589] process_one_work+0x1e6/0x380 [ 3406.232982][T230589] worker_thread+0x50/0x3a0 [ 3406.242371][T230589] ? rescuer_thread+0x360/0x360 [ 3406.252175][T230589] kthread+0x127/0x150 [ 3406.261197][T230589] ? set_kthread_struct+0x40/0x40 [ 3406.271287][T230589] ret_from_fork+0x22/0x30 [ 3406.280812][T230589] </TASK> [ 3406.288937][T230589] Modules linked in: ... [last unloaded: kheaders] [ 3406.476714][T230589] ---[ end trace 3525a7655f2f3b9e ]---

Fixes: 88e2ca308094 ("mld: convert ifmcaddr6 to RCU") Reported-by: David Pinilla Caparros dpini@cloudflare.com Signed-off-by: Ignat Korchagin ignat@cloudflare.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/addrconf.h | 2 -- net/ipv6/addrconf.c | 4 ++-- net/ipv6/mcast.c | 2 +- 3 files changed, 3 insertions(+), 5 deletions(-)

--- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -109,8 +109,6 @@ struct inet6_ifaddr *ipv6_get_ifaddr(str int ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); -int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, - u32 banned_flags); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1839,8 +1839,8 @@ out: } EXPORT_SYMBOL(ipv6_dev_get_saddr);

-int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, - u32 banned_flags) +static int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, + u32 banned_flags) { struct inet6_ifaddr *ifp; int err = -EADDRNOTAVAIL; --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1759,7 +1759,7 @@ static struct sk_buff *mld_newpack(struc skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen);

- if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { + if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available.

From: Jonas Gorski jonas.gorski@gmail.com

commit 6aba04ee3263669b335458c4cf4c7d97d6940229 upstream.

This reverts commit 3710e80952cf2dc48257ac9f145b117b5f74e0a5.

Since idm_base and nicpm_base are still optional resources not present on all platforms, this breaks the driver for everything except Northstar 2 (which has both).

The same change was already reverted once with 755f5738ff98 ("net: broadcom: fix a mistake about ioremap resource").

So let's do it again.

Fixes: 3710e80952cf ("net: ethernet: bgmac: Use devm_platform_ioremap_resource_byname") Signed-off-by: Jonas Gorski jonas.gorski@gmail.com [florian: Added comments to explain the resources are optional] Signed-off-by: Florian Fainelli f.fainelli@gmail.com Reviewed-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/20220216184634.2032460-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bgmac-platform.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-)

--- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -172,6 +172,7 @@ static int bgmac_probe(struct platform_d { struct device_node *np = pdev->dev.of_node; struct bgmac *bgmac; + struct resource *regs; int ret;

bgmac = bgmac_alloc(&pdev->dev); @@ -208,15 +209,23 @@ static int bgmac_probe(struct platform_d if (IS_ERR(bgmac->plat.base)) return PTR_ERR(bgmac->plat.base);

- bgmac->plat.idm_base = devm_platform_ioremap_resource_byname(pdev, "idm_base"); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); - else + /* The idm_base resource is optional for some platforms */ + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); + if (regs) { + bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; + }

- bgmac->plat.nicpm_base = devm_platform_ioremap_resource_byname(pdev, "nicpm_base"); - if (IS_ERR(bgmac->plat.nicpm_base)) - return PTR_ERR(bgmac->plat.nicpm_base); + /* The nicpm_base resource is optional for some platforms */ + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); + if (regs) { + bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, + regs); + if (IS_ERR(bgmac->plat.nicpm_base)) + return PTR_ERR(bgmac->plat.nicpm_base); + }

bgmac->read = platform_bgmac_read; bgmac->write = platform_bgmac_write;

From: Phil Elwell phil@raspberrypi.com

commit 665408f4c3a5c83e712871daa062721624b2b79e upstream.

The call to brcm_alt_fw_path in brcmf_fw_get_firmwares is not protected by a check to the validity of the fwctx->req->board_type pointer. This results in a crash in strlcat when, for example, the WLAN chip is found in a USB dongle.

Prevent the crash by adding the necessary check.

See: https://github.com/raspberrypi/linux/issues/4833

Fixes: 5ff013914c62 ("brcmfmac: firmware: Allow per-board firmware binaries") Signed-off-by: Phil Elwell phil@raspberrypi.com Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/20220118154514.3245524-1-phil@raspberrypi.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c @@ -693,7 +693,7 @@ int brcmf_fw_get_firmwares(struct device { struct brcmf_fw_item *first = &req->items[0]; struct brcmf_fw *fwctx; - char *alt_path; + char *alt_path = NULL; int ret;

brcmf_dbg(TRACE, "enter: dev=%s\n", dev_name(dev)); @@ -712,7 +712,9 @@ int brcmf_fw_get_firmwares(struct device fwctx->done = fw_cb;

/* First try alternative board-specific path if any */ - alt_path = brcm_alt_fw_path(first->path, fwctx->req->board_type); + if (fwctx->req->board_type) + alt_path = brcm_alt_fw_path(first->path, + fwctx->req->board_type); if (alt_path) { ret = request_firmware_nowait(THIS_MODULE, true, alt_path, fwctx->dev, GFP_KERNEL, fwctx,

From: Mans Rullgard mans@mansr.com

commit 6bb9681a43f34f2cab4aad6e2a02da4ce54d13c5 upstream.

The reset input to the LAN9303 chip is active low, and devicetree gpio handles reflect this. Therefore, the gpio should be requested with an initial state of high in order for the reset signal to be asserted. Other uses of the gpio already use the correct polarity.

Fixes: a1292595e006 ("net: dsa: add new DSA switch driver for the SMSC-LAN9303") Signed-off-by: Mans Rullgard mans@mansr.com Reviewed-by: Andrew Lunn andrew@lunn.ch Reviewed-by: Florian Fianelil f.fainelli@gmail.com Link: https://lore.kernel.org/r/20220209145454.19749-1-mans@mansr.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/lan9303-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1309,7 +1309,7 @@ static int lan9303_probe_reset_gpio(stru struct device_node *np) { chip->reset_gpio = devm_gpiod_get_optional(chip->dev, "reset", - GPIOD_OUT_LOW); + GPIOD_OUT_HIGH); if (IS_ERR(chip->reset_gpio)) return PTR_ERR(chip->reset_gpio);

From: Alexey Khoroshilov khoroshilov@ispras.ru

commit 8c6ae46150a453f8ae9a6cd49b45f354f478587d upstream.

of_node_put(priv->ds->slave_mii_bus->dev.of_node) should be done before mdiobus_free(priv->ds->slave_mii_bus).

Signed-off-by: Alexey Khoroshilov khoroshilov@ispras.ru Fixes: 0d120dfb5d67 ("net: dsa: lantiq_gswip: don't use devres for mdiobus") Reviewed-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/1644921768-26477-1-git-send-email-khoroshilov@ispr... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/lantiq_gswip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -2217,8 +2217,8 @@ static int gswip_remove(struct platform_

if (priv->ds->slave_mii_bus) { mdiobus_unregister(priv->ds->slave_mii_bus); - mdiobus_free(priv->ds->slave_mii_bus); of_node_put(priv->ds->slave_mii_bus->dev.of_node); + mdiobus_free(priv->ds->slave_mii_bus); }

for (i = 0; i < priv->num_gphy_fw; i++)

From: Mans Rullgard mans@mansr.com

commit 430065e2671905ac675f97b7af240cc255964e93 upstream.

If the master device does VLAN filtering, the IDs used by the switch must be added for any frames to be received. Do this in the port_enable() function, and remove them in port_disable().

Fixes: a1292595e006 ("net: dsa: add new DSA switch driver for the SMSC-LAN9303") Signed-off-by: Mans Rullgard mans@mansr.com Reviewed-by: Florian Fainelli f.fainelli@gmail.com Reviewed-by: Vladimir Oltean olteanv@gmail.com Link: https://lore.kernel.org/r/20220216204818.28746-1-mans@mansr.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/Kconfig | 1 + drivers/net/dsa/lan9303-core.c | 11 +++++++++-- 2 files changed, 10 insertions(+), 2 deletions(-)

--- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -82,6 +82,7 @@ config NET_DSA_REALTEK_SMI

config NET_DSA_SMSC_LAN9303 tristate + depends on VLAN_8021Q || VLAN_8021Q=n select NET_DSA_TAG_LAN9303 select REGMAP help --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -10,6 +10,7 @@ #include <linux/mii.h> #include <linux/phy.h> #include <linux/if_bridge.h> +#include <linux/if_vlan.h> #include <linux/etherdevice.h>

#include "lan9303.h" @@ -1083,21 +1084,27 @@ static void lan9303_adjust_link(struct d static int lan9303_port_enable(struct dsa_switch *ds, int port, struct phy_device *phy) { + struct dsa_port *dp = dsa_to_port(ds, port); struct lan9303 *chip = ds->priv;

- if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return 0;

+ vlan_vid_add(dp->cpu_dp->master, htons(ETH_P_8021Q), port); + return lan9303_enable_processing_port(chip, port); }

static void lan9303_port_disable(struct dsa_switch *ds, int port) { + struct dsa_port *dp = dsa_to_port(ds, port); struct lan9303 *chip = ds->priv;

- if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return;

+ vlan_vid_del(dp->cpu_dp->master, htons(ETH_P_8021Q), port); + lan9303_disable_processing_port(chip, port); lan9303_phy_write(ds, chip->phy_addr_base + port, MII_BMCR, BMCR_PDOWN); }

From: Xin Long lucien.xin@gmail.com

commit 35a79e64de29e8d57a5989aac57611c0cd29e13e upstream.

When 'ping' changes to use PING socket instead of RAW socket by:

# sysctl -w net.ipv4.ping_group_range="0 100"

There is another regression caused when matching sk_bound_dev_if and dif, RAW socket is using inet_iif() while PING socket lookup is using skb->dev->ifindex, the cmd below fails due to this:

# ip link add dummy0 type dummy # ip link set dummy0 up # ip addr add 192.168.111.1/24 dev dummy0 # ping -I dummy0 192.168.111.1 -c1

The issue was also reported on:

https://github.com/iputils/iputils/issues/104

But fixed in iputils in a wrong way by not binding to device when destination IP is on device, and it will cause some of kselftests to fail, as Jianlin noticed.

This patch is to use inet(6)_iif and inet(6)_sdif to get dif and sdif for PING socket, and keep consistent with RAW socket.

Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Reported-by: Jianlin Shi jishi@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/ping.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -172,16 +172,23 @@ static struct sock *ping_lookup(struct n struct sock *sk = NULL; struct inet_sock *isk; struct hlist_nulls_node *hnode; - int dif = skb->dev->ifindex; + int dif, sdif;

if (skb->protocol == htons(ETH_P_IP)) { + dif = inet_iif(skb); + sdif = inet_sdif(skb); pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", (int)ident, &ip_hdr(skb)->daddr, dif); #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { + dif = inet6_iif(skb); + sdif = inet6_sdif(skb); pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n", (int)ident, &ipv6_hdr(skb)->daddr, dif); #endif + } else { + pr_err("ping: protocol(%x) is not supported\n", ntohs(skb->protocol)); + return NULL; }

read_lock_bh(&ping_table.lock); @@ -221,7 +228,7 @@ static struct sock *ping_lookup(struct n }

if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && - sk->sk_bound_dev_if != inet_sdif(skb)) + sk->sk_bound_dev_if != sdif) continue;

sock_hold(sk);

From: Tom Rix trix@redhat.com

commit 7e5b6a5c8c44310784c88c1c198dde79f6402f7b upstream.

Clang static analysis reports this problem route.c:425:4: warning: Use of memory after it is freed trace_mctp_key_acquire(key); ^~~~~~~~~~~~~~~~~~~~~~~~~~~ When mctp_key_add() fails, key is freed but then is later used in trace_mctp_key_acquire(). Add an else statement to use the key only when mctp_key_add() is successful.

Fixes: 4f9e1ba6de45 ("mctp: Add tracepoints for tag/key handling") Signed-off-by: Tom Rix trix@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mctp/route.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

--- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -414,13 +414,14 @@ static int mctp_route_input(struct mctp_ * this function. */ rc = mctp_key_add(key, msk); - if (rc) + if (rc) { kfree(key); + } else { + trace_mctp_key_acquire(key);

- trace_mctp_key_acquire(key); - - /* we don't need to release key->lock on exit */ - mctp_key_unref(key); + /* we don't need to release key->lock on exit */ + mctp_key_unref(key); + } key = NULL;

} else {

From: Eric Dumazet edumazet@google.com

commit 5891cd5ec46c2c2eb6427cb54d214b149635dd0e upstream.

syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support.

[1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu

write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Vlad Buslov vladbu@mellanox.com Reported-by: syzbot syzkaller@googlegroups.com Cc: Jamal Hadi Salim jhs@mojatatu.com Cc: Cong Wang xiyou.wangcong@gmail.com Cc: Jiri Pirko jiri@resnulli.us Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/netdevice.h | 2 +- net/core/rtnetlink.c | 6 ++++-- net/sched/cls_api.c | 6 +++--- net/sched/sch_api.c | 22 ++++++++++++---------- net/sched/sch_generic.c | 29 ++++++++++++++++------------- 5 files changed, 36 insertions(+), 29 deletions(-)

--- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2149,7 +2149,7 @@ struct net_device { struct netdev_queue *_tx ____cacheline_aligned_in_smp; unsigned int num_tx_queues; unsigned int real_num_tx_queues; - struct Qdisc *qdisc; + struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock;

--- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1698,6 +1698,7 @@ static int rtnl_fill_ifinfo(struct sk_bu { struct ifinfomsg *ifm; struct nlmsghdr *nlh; + struct Qdisc *qdisc;

ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -1715,6 +1716,7 @@ static int rtnl_fill_ifinfo(struct sk_bu if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) goto nla_put_failure;

+ qdisc = rtnl_dereference(dev->qdisc); if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || nla_put_u8(skb, IFLA_OPERSTATE, @@ -1733,8 +1735,8 @@ static int rtnl_fill_ifinfo(struct sk_bu #endif put_master_ifindex(skb, dev) || nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || - (dev->qdisc && - nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || + (qdisc && + nla_put_string(skb, IFLA_QDISC, qdisc->ops->id)) || nla_put_ifalias(skb, dev) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, atomic_read(&dev->carrier_up_count) + --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1044,7 +1044,7 @@ static int __tcf_qdisc_find(struct net *

/* Find qdisc */ if (!*parent) { - *q = dev->qdisc; + *q = rcu_dereference(dev->qdisc); *parent = (*q)->handle; } else { *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); @@ -2587,7 +2587,7 @@ static int tc_dump_tfilter(struct sk_buf

parent = tcm->tcm_parent; if (!parent) - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); if (!q) @@ -2962,7 +2962,7 @@ static int tc_dump_chain(struct sk_buff return skb->len;

if (!tcm->tcm_parent) - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));

--- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -301,7 +301,7 @@ struct Qdisc *qdisc_lookup(struct net_de

if (!handle) return NULL; - q = qdisc_match_from_root(dev->qdisc, handle); + q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle); if (q) goto out;

@@ -320,7 +320,7 @@ struct Qdisc *qdisc_lookup_rcu(struct ne

if (!handle) return NULL; - q = qdisc_match_from_root(dev->qdisc, handle); + q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle); if (q) goto out;

@@ -1082,10 +1082,10 @@ static int qdisc_graft(struct net_device skip: if (!ingress) { notify_and_destroy(net, skb, n, classid, - dev->qdisc, new); + rtnl_dereference(dev->qdisc), new); if (new && !new->ops->attach) qdisc_refcount_inc(new); - dev->qdisc = new ? : &noop_qdisc; + rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc);

if (new && new->ops->attach) new->ops->attach(new); @@ -1451,7 +1451,7 @@ static int tc_get_qdisc(struct sk_buff * q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); } if (!q) { NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); @@ -1540,7 +1540,7 @@ replay: q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); }

/* It may be default qdisc, ignore it */ @@ -1762,7 +1762,8 @@ static int tc_dump_qdisc(struct sk_buff s_q_idx = 0; q_idx = 0;

- if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, + if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc), + skb, cb, &q_idx, s_q_idx, true, tca[TCA_DUMP_INVISIBLE]) < 0) goto done;

@@ -2033,7 +2034,7 @@ static int tc_ctl_tclass(struct sk_buff } else if (qid1) { qid = qid1; } else if (qid == 0) - qid = dev->qdisc->handle; + qid = rtnl_dereference(dev->qdisc)->handle;

/* Now qid is genuine qdisc handle consistent * both with parent and child. @@ -2044,7 +2045,7 @@ static int tc_ctl_tclass(struct sk_buff portid = TC_H_MAKE(qid, portid); } else { if (qid == 0) - qid = dev->qdisc->handle; + qid = rtnl_dereference(dev->qdisc)->handle; }

/* OK. Locate qdisc */ @@ -2205,7 +2206,8 @@ static int tc_dump_tclass(struct sk_buff s_t = cb->args[0]; t = 0;

- if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0) + if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc), + skb, tcm, cb, &t, s_t, true) < 0) goto done;

dev_queue = dev_ingress_queue(dev); --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1109,30 +1109,33 @@ static void attach_default_qdiscs(struct if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - dev->qdisc = txq->qdisc_sleeping; - qdisc_refcount_inc(dev->qdisc); + qdisc = txq->qdisc_sleeping; + rcu_assign_pointer(dev->qdisc, qdisc); + qdisc_refcount_inc(qdisc); } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL); if (qdisc) { - dev->qdisc = qdisc; + rcu_assign_pointer(dev->qdisc, qdisc); qdisc->ops->attach(qdisc); } } + qdisc = rtnl_dereference(dev->qdisc);

/* Detect default qdisc setup/init failed and fallback to "noqueue" */ - if (dev->qdisc == &noop_qdisc) { + if (qdisc == &noop_qdisc) { netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n", default_qdisc_ops->id, noqueue_qdisc_ops.id); dev->priv_flags |= IFF_NO_QUEUE; netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - dev->qdisc = txq->qdisc_sleeping; - qdisc_refcount_inc(dev->qdisc); + qdisc = txq->qdisc_sleeping; + rcu_assign_pointer(dev->qdisc, qdisc); + qdisc_refcount_inc(qdisc); dev->priv_flags ^= IFF_NO_QUEUE; }

#ifdef CONFIG_NET_SCHED - if (dev->qdisc != &noop_qdisc) - qdisc_hash_add(dev->qdisc, false); + if (qdisc != &noop_qdisc) + qdisc_hash_add(qdisc, false); #endif }

@@ -1162,7 +1165,7 @@ void dev_activate(struct net_device *dev * and noqueue_qdisc for virtual interfaces */

- if (dev->qdisc == &noop_qdisc) + if (rtnl_dereference(dev->qdisc) == &noop_qdisc) attach_default_qdiscs(dev);

if (!netif_carrier_ok(dev)) @@ -1328,7 +1331,7 @@ static int qdisc_change_tx_queue_len(str void dev_qdisc_change_real_num_tx(struct net_device *dev, unsigned int new_real_tx) { - struct Qdisc *qdisc = dev->qdisc; + struct Qdisc *qdisc = rtnl_dereference(dev->qdisc);

if (qdisc->ops->change_real_num_tx) qdisc->ops->change_real_num_tx(qdisc, new_real_tx); @@ -1392,7 +1395,7 @@ static void dev_init_scheduler_queue(str

void dev_init_scheduler(struct net_device *dev) { - dev->qdisc = &noop_qdisc; + rcu_assign_pointer(dev->qdisc, &noop_qdisc); netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); @@ -1420,8 +1423,8 @@ void dev_shutdown(struct net_device *dev netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - qdisc_put(dev->qdisc); - dev->qdisc = &noop_qdisc; + qdisc_put(rtnl_dereference(dev->qdisc)); + rcu_assign_pointer(dev->qdisc, &noop_qdisc);

WARN_ON(timer_pending(&dev->watchdog_timer)); }

From: Eric Dumazet edumazet@google.com

commit 9ceaf6f76b203682bb6100e14b3d7da4c0bedde8 upstream.

syzbot reported that two threads might write over agg_select_timer at the same time. Make agg_select_timer atomic to fix the races.

BUG: KCSAN: data-race in bond_3ad_initiate_agg_selection / bond_3ad_state_machine_handler

read to 0xffff8881242aea90 of 4 bytes by task 1846 on cpu 1: bond_3ad_state_machine_handler+0x99/0x2810 drivers/net/bonding/bond_3ad.c:2317 process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 worker_thread+0x616/0xa70 kernel/workqueue.c:2454 kthread+0x1bf/0x1e0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30

write to 0xffff8881242aea90 of 4 bytes by task 25910 on cpu 0: bond_3ad_initiate_agg_selection+0x18/0x30 drivers/net/bonding/bond_3ad.c:1998 bond_open+0x658/0x6f0 drivers/net/bonding/bond_main.c:3967 __dev_open+0x274/0x3a0 net/core/dev.c:1407 dev_open+0x54/0x190 net/core/dev.c:1443 bond_enslave+0xcef/0x3000 drivers/net/bonding/bond_main.c:1937 do_set_master net/core/rtnetlink.c:2532 [inline] do_setlink+0x94f/0x2500 net/core/rtnetlink.c:2736 __rtnl_newlink net/core/rtnetlink.c:3414 [inline] rtnl_newlink+0xfeb/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0x00000050 -> 0x0000004f

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 25910 Comm: syz-executor.1 Tainted: G W 5.17.0-rc4-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: Jay Vosburgh j.vosburgh@gmail.com Cc: Veaceslav Falico vfalico@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/bonding/bond_3ad.c | 30 +++++++++++++++++++++++++----- include/net/bond_3ad.h | 2 +- 2 files changed, 26 insertions(+), 6 deletions(-)

--- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -225,7 +225,7 @@ static inline int __check_agg_selection_ if (bond == NULL) return 0;

- return BOND_AD_INFO(bond).agg_select_timer ? 1 : 0; + return atomic_read(&BOND_AD_INFO(bond).agg_select_timer) ? 1 : 0; }

/** @@ -1995,7 +1995,7 @@ static void ad_marker_response_received( */ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) { - BOND_AD_INFO(bond).agg_select_timer = timeout; + atomic_set(&BOND_AD_INFO(bond).agg_select_timer, timeout); }

/** @@ -2279,6 +2279,28 @@ void bond_3ad_update_ad_actor_settings(s }

/** + * bond_agg_timer_advance - advance agg_select_timer + * @bond: bonding structure + * + * Return true when agg_select_timer reaches 0. + */ +static bool bond_agg_timer_advance(struct bonding *bond) +{ + int val, nval; + + while (1) { + val = atomic_read(&BOND_AD_INFO(bond).agg_select_timer); + if (!val) + return false; + nval = val - 1; + if (atomic_cmpxchg(&BOND_AD_INFO(bond).agg_select_timer, + val, nval) == val) + break; + } + return nval == 0; +} + +/** * bond_3ad_state_machine_handler - handle state machines timeout * @work: work context to fetch bonding struct to work on from * @@ -2313,9 +2335,7 @@ void bond_3ad_state_machine_handler(stru if (!bond_has_slaves(bond)) goto re_arm;

- /* check if agg_select_timer timer after initialize is timed out */ - if (BOND_AD_INFO(bond).agg_select_timer && - !(--BOND_AD_INFO(bond).agg_select_timer)) { + if (bond_agg_timer_advance(bond)) { slave = bond_first_slave_rcu(bond); port = slave ? &(SLAVE_AD_INFO(slave)->port) : NULL;

--- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -262,7 +262,7 @@ struct ad_system { struct ad_bond_info { struct ad_system system; /* 802.3ad system structure */ struct bond_3ad_stats stats; - u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ + atomic_t agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ u16 aggregator_identifier; };

From: Kees Cook keescook@chromium.org

commit 52a9dab6d892763b2a8334a568bd4e2c1a6fde66 upstream.

GCC 12 correctly reports a potential use-after-free condition in the xrealloc helper. Fix the warning by avoiding an implicit "free(ptr)" when size == 0:

In file included from help.c:12: In function 'xrealloc', inlined from 'add_cmdname' at help.c:24:2: subcmd-util.h:56:23: error: pointer may be used after 'realloc' [-Werror=use-after-free] 56 | ret = realloc(ptr, size); | ^~~~~~~~~~~~~~~~~~ subcmd-util.h:52:21: note: call to 'realloc' here 52 | void *ret = realloc(ptr, size); | ^~~~~~~~~~~~~~~~~~ subcmd-util.h:58:31: error: pointer may be used after 'realloc' [-Werror=use-after-free] 58 | ret = realloc(ptr, 1); | ^~~~~~~~~~~~~~~ subcmd-util.h:52:21: note: call to 'realloc' here 52 | void *ret = realloc(ptr, size); | ^~~~~~~~~~~~~~~~~~

Fixes: 2f4ce5ec1d447beb ("perf tools: Finalize subcmd independence") Reported-by: Valdis Klētnieks valdis.kletnieks@vt.edu Signed-off-by: Kees Kook keescook@chromium.org Tested-by: Valdis Klētnieks valdis.kletnieks@vt.edu Tested-by: Justin M. Forbes jforbes@fedoraproject.org Acked-by: Josh Poimboeuf jpoimboe@redhat.com Cc: linux-hardening@vger.kernel.org Cc: Valdis Klētnieks valdis.kletnieks@vt.edu Link: http://lore.kernel.org/lkml/20220213182443.4037039-1-keescook@chromium.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/lib/subcmd/subcmd-util.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-)

--- a/tools/lib/subcmd/subcmd-util.h +++ b/tools/lib/subcmd/subcmd-util.h @@ -50,15 +50,8 @@ static NORETURN inline void die(const ch static inline void *xrealloc(void *ptr, size_t size) { void *ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) { - ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) - die("Out of memory, realloc failed"); - } + if (!ret) + die("Out of memory, realloc failed"); return ret; }

From: DENG Qingfang dqfext@gmail.com

commit 525b108e6d95b643eccbd84fb10aa9aa101b18dd upstream.

The function mt7531_phy_mode_supported in the DSA driver set supported mode to PHY_INTERFACE_MODE_GMII instead of PHY_INTERFACE_MODE_INTERNAL for the internal PHY, so this check breaks the PHY initialization:

mt7530 mdio-bus:00 wan (uninitialized): failed to connect to PHY: -EINVAL

Remove the check to make it work again.

Reported-by: Hauke Mehrtens hauke@hauke-m.de Fixes: e40d2cca0189 ("net: phy: add MediaTek Gigabit Ethernet PHY driver") Signed-off-by: DENG Qingfang dqfext@gmail.com Acked-by: Arınç ÜNAL arinc.unal@arinc9.com Tested-by: Hauke Mehrtens hauke@hauke-m.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/mediatek-ge.c | 3 --- 1 file changed, 3 deletions(-)

--- a/drivers/net/phy/mediatek-ge.c +++ b/drivers/net/phy/mediatek-ge.c @@ -55,9 +55,6 @@ static int mt7530_phy_config_init(struct

static int mt7531_phy_config_init(struct phy_device *phydev) { - if (phydev->interface != PHY_INTERFACE_MODE_INTERNAL) - return -EINVAL; - mtk_gephy_config_init(phydev);

/* PHY link down power saving enable */

From: Jon Maloy jmaloy@redhat.com

commit 032062f363b4bf02b1d547f329aa5d97b6a17410 upstream.

When a link comes up we add its presence to the name table to make it possible for users to subscribe for link up/down events. However, after a previous call signature change the binding is wrongly published with the peer node as publishing node, instead of the own node as it should be. This has the effect that the command 'tipc name table show' will list the link binding (service type 2) with node scope and a peer node as originator, something that obviously is impossible.

We correct this bug here.

Fixes: 50a3499ab853 ("tipc: simplify signature of tipc_namtbl_publish()") Signed-off-by: Jon Maloy jmaloy@redhat.com Link: https://lore.kernel.org/r/20220214013852.2803940-1-jmaloy@redhat.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/tipc/node.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -413,7 +413,7 @@ static void tipc_node_write_unlock(struc tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE, TIPC_LINK_STATE, n->addr, n->addr); sk.ref = n->link_id; - sk.node = n->addr; + sk.node = tipc_own_addr(net); bearer_id = n->link_id & 0xffff; publ_list = &n->publ_list;

From: Radu Bulie radu-andrei.bulie@nxp.com

commit 07dd44852be89386ab12210df90a2d78779f3bff upstream.

1588 Single Step Timestamping code path uses a mutex to enforce atomicity for two events: - update of ptp single step register - transmit ptp event packet

Before this patch the mutex was not initialized. This caused unexpected crashes in the Tx function.

Fixes: c55211892f463 ("dpaa2-eth: support PTP Sync packet one-step timestamping") Signed-off-by: Radu Bulie radu-andrei.bulie@nxp.com Reviewed-by: Ioana Ciornei ioana.ciornei@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4338,7 +4338,7 @@ static int dpaa2_eth_probe(struct fsl_mc }

INIT_WORK(&priv->tx_onestep_tstamp, dpaa2_eth_tx_onestep_tstamp); - + mutex_init(&priv->onestep_tstamp_lock); skb_queue_head_init(&priv->tx_skbs);

priv->rx_copybreak = DPAA2_ETH_DEFAULT_COPYBREAK;

From: Oleksandr Mazur oleksandr.mazur@plvision.eu

commit c832962ac972082b3a1f89775c9d4274c8cb5670 upstream.

Whenever bridge driver hits the max capacity of MDBs, it disables the MC processing (by setting corresponding bridge option), but never notifies switchdev about such change (the notifiers are called only upon explicit setting of this option, through the registered netlink interface).

This could lead to situation when Software MDB processing gets disabled, but this event never gets offloaded to the underlying Hardware.

Fix this by adding a notify message in such case.

Fixes: 147c1e9b902c ("switchdev: bridge: Offload multicast disabled") Signed-off-by: Oleksandr Mazur oleksandr.mazur@plvision.eu Acked-by: Nikolay Aleksandrov nikolay@nvidia.com Link: https://lore.kernel.org/r/20220215165303.31908-1-oleksandr.mazur@plvision.eu Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_multicast.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -82,6 +82,9 @@ static void br_multicast_find_del_pg(str struct net_bridge_port_group *pg); static void __br_multicast_stop(struct net_bridge_mcast *brmctx);

+static int br_mc_disabled_update(struct net_device *dev, bool value, + struct netlink_ext_ack *extack); + static struct net_bridge_port_group * br_sg_port_find(struct net_bridge *br, struct net_bridge_port_group_sg_key *sg_p) @@ -1156,6 +1159,7 @@ struct net_bridge_mdb_entry *br_multicas return mp;

if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) { + br_mc_disabled_update(br->dev, false, NULL); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false); return ERR_PTR(-E2BIG); }

From: Muhammad Usama Anjum usama.anjum@collabora.com

commit a7e793a867ae312cecdeb6f06cceff98263e75dd upstream.

non-regular file needs to be compiled and then copied to the output directory. Remove it from TEST_PROGS and add it to TEST_GEN_PROGS. This removes error thrown by rsync when non-regular object isn't found:

rsync: [sender] link_stat "/linux/tools/testing/selftests/exec/non-regular" failed: No such file or directory (2) rsync error: some files/attrs were not transferred (see previous errors) (code 23) at main.c(1333) [sender=3.2.3]

Fixes: 0f71241a8e32 ("selftests/exec: add file type errno tests") Reported-by: "kernelci.org bot" bot@kernelci.org Signed-off-by: Muhammad Usama Anjum usama.anjum@collabora.com Reviewed-by: Shuah Khan skhan@linuxfoundation.org Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/exec/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -3,8 +3,8 @@ CFLAGS = -Wall CFLAGS += -Wno-nonnull CFLAGS += -D_GNU_SOURCE

-TEST_PROGS := binfmt_script non-regular -TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 +TEST_PROGS := binfmt_script +TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 non-regular TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir # Makefile is a run-time dependency, since it's accessed by the execveat test TEST_FILES := Makefile

From: Takashi Iwai tiwai@suse.de

commit 9a5adeb28b77416446658e75bdef3bbe5fb92a83 upstream.

The default mixer resume code treats the errors at restoring the modified mixer items as a fatal error, and it returns back to the caller. This ends up in the resume failure, and the device will be come unavailable, although basically those errors are intermittent and can be safely ignored.

The problem itself has been present from the beginning, but it didn't hit usually because the code tries to resume only the modified items. But now with the recent commit to forcibly initialize each item at the probe time, the problem surfaced more often, hence it appears as a regression.

This patch fixes the regression simply by ignoring the errors at resume.

Fixes: b96681bd5827 ("ALSA: usb-audio: Initialize every feature unit once at probe time") Cc: stable@vger.kernel.org BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=215561 Link: https://lore.kernel.org/r/20220214125711.20531-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/mixer.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

--- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -3678,17 +3678,14 @@ static int restore_mixer_value(struct us err = snd_usb_set_cur_mix_value(cval, c + 1, idx, cval->cache_val[idx]); if (err < 0) - return err; + break; } idx++; } } else { /* master */ - if (cval->cached) { - err = snd_usb_set_cur_mix_value(cval, 0, 0, *cval->cache_val); - if (err < 0) - return err; - } + if (cval->cached) + snd_usb_set_cur_mix_value(cval, 0, 0, *cval->cache_val); }

return 0;

From: Takashi Iwai tiwai@suse.de

commit 8e1741c658996a16bd096e077dae0da2460a997f upstream.

dma_need_sync() checks each DMA address. Fix the incorrect usages for non-contiguous and non-coherent page allocations. Fortunately, there are no actual call sites that need manual syncs yet.

Fixes: a25684a95646 ("ALSA: memalloc: Support for non-contiguous page allocation") Fixes: 73325f60e2ed ("ALSA: memalloc: Support for non-coherent page allocation") Cc: stable@vger.kernel.org Reported-by: Ezequiel Garcia ezequiel@vanguardiasur.com.ar Link: https://lore.kernel.org/r/20220210123344.8756-2-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/core/memalloc.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)

--- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -511,7 +511,8 @@ static void *snd_dma_noncontig_alloc(str DEFAULT_GFP, 0); if (!sgt) return NULL; - dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, dmab->dev.dir); + dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, + sg_dma_address(sgt->sgl)); p = dma_vmap_noncontiguous(dmab->dev.dev, size, sgt); if (p) dmab->private_data = sgt; @@ -625,9 +626,13 @@ static const struct snd_malloc_ops snd_d */ static void *snd_dma_noncoherent_alloc(struct snd_dma_buffer *dmab, size_t size) { - dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, dmab->dev.dir); - return dma_alloc_noncoherent(dmab->dev.dev, size, &dmab->addr, - dmab->dev.dir, DEFAULT_GFP); + void *p; + + p = dma_alloc_noncoherent(dmab->dev.dev, size, &dmab->addr, + dmab->dev.dir, DEFAULT_GFP); + if (p) + dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, dmab->addr); + return p; }

static void snd_dma_noncoherent_free(struct snd_dma_buffer *dmab)

From: Yu Huang diwang90@gmail.com

commit c07f2c7b45413a9e50ba78630fda04ecfa17b4f2 upstream.

Legion Y9000X 2019 has the same speaker with Y9000X 2020, but with a different quirk address. Add one quirk entry to make the speaker work on Y9000X 2019 too.

Signed-off-by: Yu Huang diwang90@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220212160835.165065-1-diwang90@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9013,6 +9013,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x17aa, 0x3824, "Legion Y9000X 2020", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x383d, "Legion Y9000X 2019", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP), SND_PCI_QUIRK(0x17aa, 0x384a, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),

From: Takashi Iwai tiwai@suse.de

commit 6317f7449348a897483a2b4841f7a9190745c81b upstream.

The forced probe mask via probe_mask 0x100 bit doesn't work any longer as expected since the bus init code was moved and it's clearing the codec_mask value that was set beforehand. This patch fixes the long-time regression by moving the check_probe_mask() call.

Fixes: a41d122449be ("ALSA: hda - Embed bus into controller object") Reported-by: dmummenschanz@web.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/trinity-f018660b-95c9-442b-a2a8-c92a56eb07ed-16443... Link: https://lore.kernel.org/r/20220214100020.8870-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/hda_intel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1794,8 +1794,6 @@ static int azx_create(struct snd_card *c

assign_position_fix(chip, check_position_fix(chip, position_fix[dev]));

- check_probe_mask(chip, dev); - if (single_cmd < 0) /* allow fallback to single_cmd at errors */ chip->fallback_to_single_cmd = 1; else /* explicitly set to single_cmd or not */ @@ -1821,6 +1819,8 @@ static int azx_create(struct snd_card *c chip->bus.core.needs_damn_long_delay = 1; }

+ check_probe_mask(chip, dev); + err = snd_device_new(card, SNDRV_DEV_LOWLEVEL, chip, &ops); if (err < 0) { dev_err(card->dev, "Error creating device [card]!\n");

From: Mark Brown broonie@kernel.org

commit 564778d7b1ea465f9487eedeece7527a033549c5 upstream.

When writing out a stereo control we discard the change notification from the first channel, meaning that events are only generated based on changes to the second channel. Ensure that we report a change if either channel has changed.

Signed-off-by: Mark Brown broonie@kernel.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220201155629.120510-2-broonie@kernel.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/soc-ops.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)

--- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -308,7 +308,7 @@ int snd_soc_put_volsw(struct snd_kcontro unsigned int sign_bit = mc->sign_bit; unsigned int mask = (1 << fls(max)) - 1; unsigned int invert = mc->invert; - int err; + int err, ret; bool type_2r = false; unsigned int val2 = 0; unsigned int val, val_mask; @@ -350,12 +350,18 @@ int snd_soc_put_volsw(struct snd_kcontro err = snd_soc_component_update_bits(component, reg, val_mask, val); if (err < 0) return err; + ret = err;

- if (type_2r) + if (type_2r) { err = snd_soc_component_update_bits(component, reg2, val_mask, - val2); + val2); + /* Don't discard any error code or drop change flag */ + if (ret == 0 || err < 0) { + ret = err; + } + }

- return err; + return ret; } EXPORT_SYMBOL_GPL(snd_soc_put_volsw);

From: Mark Brown broonie@kernel.org

commit 7f3d90a3519680dfa23e750f80bfdefc0f5eda4a upstream.

When writing out a stereo control we discard the change notification from the first channel, meaning that events are only generated based on changes to the second channel. Ensure that we report a change if either channel has changed.

Signed-off-by: Mark Brown broonie@kernel.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220201155629.120510-3-broonie@kernel.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/soc-ops.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -427,6 +427,7 @@ int snd_soc_put_volsw_sx(struct snd_kcon int min = mc->min; unsigned int mask = (1U << (fls(min + max) - 1)) - 1; int err = 0; + int ret; unsigned int val, val_mask;

val = ucontrol->value.integer.value[0]; @@ -443,6 +444,7 @@ int snd_soc_put_volsw_sx(struct snd_kcon err = snd_soc_component_update_bits(component, reg, val_mask, val); if (err < 0) return err; + ret = err;

if (snd_soc_volsw_is_stereo(mc)) { unsigned int val2; @@ -453,6 +455,11 @@ int snd_soc_put_volsw_sx(struct snd_kcon

err = snd_soc_component_update_bits(component, reg2, val_mask, val2); + + /* Don't discard any error code or drop change flag */ + if (ret == 0 || err < 0) { + ret = err; + } } return err; }

From: Amir Goldstein amir73il@gmail.com

commit dd5a927e411836eaef44eb9b00fece615e82e242 upstream.

'setcifsacl -g <SID>' silently fails to set the group SID on server.

Actually, the bug existed since commit 438471b67963 ("CIFS: Add support for setting owner info, dos attributes, and create time"), but this fix will not apply cleanly to kernel versions <= v5.10.

Fixes: 3970acf7ddb9 ("SMB3: Add support for getting and setting SACLs") Cc: stable@vger.kernel.org # 5.11+ Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/xattr.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -175,11 +175,13 @@ static int cifs_xattr_set(const struct x switch (handler->flags) { case XATTR_CIFS_NTSD_FULL: aclflags = (CIFS_ACL_OWNER | + CIFS_ACL_GROUP | CIFS_ACL_DACL | CIFS_ACL_SACL); break; case XATTR_CIFS_NTSD: aclflags = (CIFS_ACL_OWNER | + CIFS_ACL_GROUP | CIFS_ACL_DACL); break; case XATTR_CIFS_ACL:

From: Woody Suwalski wsuwalski@gmail.com

commit bfe55a1f7fd6bfede16078bf04c6250fbca11588 upstream.

Add and ACPI idle power level limit for 32-bit ThinkPad T40.

There is a regression on T40 introduced by commit d6b88ce2, starting with kernel 5.16:

commit d6b88ce2eb9d2698eb24451eb92c0a1649b17bb1 Author: Richard Gong richard.gong@amd.com Date:   Wed Sep 22 08:31:16 2021 -0500

ACPI: processor idle: Allow playing dead in C3 state

The above patch is trying to enter C3 state during init, what is causing a T40 system freeze. I have not found a similar issue on any other of my 32-bit machines.

The fix is to add another exception to the processor_power_dmi_table[] list. As a result the dmesg shows as expected:

[2.155398] ACPI: IBM ThinkPad T40 detected - limiting to C2 max_cstate. Override with "processor.max_cstate=9" [2.155404] ACPI: processor limited to max C-state 2

The fix is trivial and affects only vintage T40 systems.

Fixes: d6b88ce2eb9d ("CPI: processor idle: Allow playing dead in C3 state") Signed-off-by: Woody Suwalski wsuwalski@gmail.com Reviewed-by: Hans de Goede hdegoede@redhat.com Cc: 5.16+ stable@vger.kernel.org # 5.16+ [ rjw: New subject ] Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/acpi/processor_idle.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -95,6 +95,11 @@ static const struct dmi_system_id proces DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME,"L8400B series Notebook PC")}, (void *)1}, + /* T40 can not handle C3 idle state */ + { set_max_cstate, "IBM ThinkPad T40", { + DMI_MATCH(DMI_SYS_VENDOR, "IBM"), + DMI_MATCH(DMI_PRODUCT_NAME, "23737CU")}, + (void *)2}, {}, };

From: Anders Roxell anders.roxell@linaro.org

commit fe663df7825811358531dc2e8a52d9eaa5e3515e upstream.

Building tinyconfig with gcc (Debian 11.2.0-16) and assembler (Debian 2.37.90.20220207) the following build error shows up:

{standard input}: Assembler messages: {standard input}:2088: Error: unrecognized opcode: `ptesync' make[3]: *** [/builds/linux/scripts/Makefile.build:287: arch/powerpc/lib/sstep.o] Error 1

Add the 'ifdef CONFIG_PPC64' around the 'ptesync' in function 'emulate_update_regs()' to like it is in 'analyse_instr()'. Since it looks like it got dropped inadvertently by commit 3cdfcbfd32b9 ("powerpc: Change analyse_instr so it doesn't modify *regs").

A key detail is that analyse_instr() will never recognise lwsync or ptesync on 32-bit (because of the existing ifdef), and as a result emulate_update_regs() should never be called with an op specifying either of those on 32-bit. So removing them from emulate_update_regs() should be a nop in terms of runtime behaviour.

Fixes: 3cdfcbfd32b9 ("powerpc: Change analyse_instr so it doesn't modify *regs") Cc: stable@vger.kernel.org # v4.14+ Suggested-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Anders Roxell anders.roxell@linaro.org [mpe: Add last paragraph of change log mentioning analyse_instr() details] Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20220211005113.1361436-1-anders.roxell@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/lib/sstep.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -3264,12 +3264,14 @@ void emulate_update_regs(struct pt_regs case BARRIER_EIEIO: eieio(); break; +#ifdef CONFIG_PPC64 case BARRIER_LWSYNC: asm volatile("lwsync" : : : "memory"); break; case BARRIER_PTESYNC: asm volatile("ptesync" : : : "memory"); break; +#endif } break;

From: Steve French stfrench@microsoft.com

commit 9405b5f8b20c2bfa6523a555279a0379640dc136 upstream.

The conversion to the new API broke the snapshot mount option due to 32 vs. 64 bit type mismatch

Fixes: 24e0a1eff9e2 ("cifs: switch to new mount api") Cc: stable@vger.kernel.org # 5.11+ Reported-by: ruckajan10@gmail.com Acked-by: Ronnie Sahlberg lsahlber@redhat.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/fs_context.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -147,7 +147,7 @@ const struct fs_parameter_spec smb3_fs_p fsparam_u32("echo_interval", Opt_echo_interval), fsparam_u32("max_credits", Opt_max_credits), fsparam_u32("handletimeout", Opt_handletimeout), - fsparam_u32("snapshot", Opt_snapshot), + fsparam_u64("snapshot", Opt_snapshot), fsparam_u32("max_channels", Opt_max_channels),

/* Mount options which take string value */ @@ -1072,7 +1072,7 @@ static int smb3_fs_context_parse_param(s ctx->echo_interval = result.uint_32; break; case Opt_snapshot: - ctx->snapshot_time = result.uint_32; + ctx->snapshot_time = result.uint_64; break; case Opt_max_credits: if (result.uint_32 < 20 || result.uint_32 > 60000) {

From: Bart Van Assche bvanassche@acm.org

commit d77ea8226b3be23b0b45aa42851243b62a27bda1 upstream.

Commit 7252a3603015 ("scsi: ufs: Avoid busy-waiting by eliminating tag conflicts") guarantees that 'tag' is not in use by any SCSI command. Remove the check that returns early if a conflict occurs.

Link: https://lore.kernel.org/r/20211203231950.193369-6-bvanassche@acm.org Tested-by: Bean Huo beanhuo@micron.com Reviewed-by: Bean Huo beanhuo@micron.com Acked-by: Avri Altman avri.altman@wdc.com Signed-off-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/ufs/ufshcd.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-)

--- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -6734,11 +6734,6 @@ static int ufshcd_issue_devman_upiu_cmd( tag = req->tag; WARN_ONCE(tag < 0, "Invalid tag %d\n", tag);

- if (unlikely(test_bit(tag, &hba->outstanding_reqs))) { - err = -EBUSY; - goto out; - } - lrbp = &hba->lrb[tag]; WARN_ON(lrbp->cmd); lrbp->cmd = NULL; @@ -6806,8 +6801,8 @@ static int ufshcd_issue_devman_upiu_cmd( ufshcd_add_query_upiu_trace(hba, err ? UFS_QUERY_ERR : UFS_QUERY_COMP, (struct utp_upiu_req *)lrbp->ucd_rsp_ptr);

-out: blk_mq_free_request(req); + out_unlock: up_read(&hba->clk_scaling_lock); return err;