Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Lots of overlapping changes.  Also on the net-next side
the XDP state management is handled more in the generic
layers so undo the 'net' nfp fix which isn't applicable
in net-next.

Include a necessary change by Jakub Kicinski, with log message:

====================
cls_bpf no longer takes care of offload tracking.  Make sure
netdevsim performs necessary checks.  This fixes a warning
caused by TC trying to remove a filter it has not added.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 183 insertions, 129 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 48b2901cf483..1cd2c2d28fc3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1417,6 +1417,11 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
 		break;
 	case PTR_TO_STACK:
 		pointer_desc = "stack ";
+		/* The stack spill tracking logic in check_stack_write()
+		 * and check_stack_read() relies on stack accesses being
+		 * aligned.
+		 */
+		strict = true;
 		break;
 	default:
 		break;
@@ -1473,6 +1478,29 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
 	return env->subprog_stack_depth[subprog];
 }
 
+/* truncate register to smaller size (in bytes)
+ * must be called with size < BPF_REG_SIZE
+ */
+static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
+{
+	u64 mask;
+
+	/* clear high bits in bit representation */
+	reg->var_off = tnum_cast(reg->var_off, size);
+
+	/* fix arithmetic bounds */
+	mask = ((u64)1 << (size * 8)) - 1;
+	if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) {
+		reg->umin_value &= mask;
+		reg->umax_value &= mask;
+	} else {
+		reg->umin_value = 0;
+		reg->umax_value = mask;
+	}
+	reg->smin_value = reg->umin_value;
+	reg->smax_value = reg->umax_value;
+}
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -1608,9 +1636,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
 	    regs[value_regno].type == SCALAR_VALUE) {
 		/* b/h/w load zero-extends, mark upper bits as known 0 */
-		regs[value_regno].var_off =
-			tnum_cast(regs[value_regno].var_off, size);
-		__update_reg_bounds(&regs[value_regno]);
+		coerce_reg_to_size(&regs[value_regno], size);
 	}
 	return err;
 }
@@ -1684,6 +1710,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
 		verbose(env, "invalid variable stack read R%d var_off=%s\n",
 			regno, tn_buf);
+		return -EACCES;
 	}
 	off = reg->off + reg->var_off.value;
 	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
@@ -2206,7 +2233,13 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		return -EINVAL;
 	}
 
+	/* With LD_ABS/IND some JITs save/restore skb from r1. */
 	changes_data = bpf_helper_changes_pkt_data(fn->func);
+	if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
+		verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
+			func_id_name(func_id), func_id);
+		return -EINVAL;
+	}
 
 	memset(&meta, 0, sizeof(meta));
 	meta.pkt_access = fn->pkt_access;
@@ -2298,14 +2331,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	return 0;
 }
 
-static void coerce_reg_to_32(struct bpf_reg_state *reg)
-{
-	/* clear high 32 bits */
-	reg->var_off = tnum_cast(reg->var_off, 4);
-	/* Update bounds */
-	__update_reg_bounds(reg);
-}
-
 static bool signed_add_overflows(s64 a, s64 b)
 {
 	/* Do the add in u64, where overflow is well-defined */
@@ -2326,6 +2351,41 @@ static bool signed_sub_overflows(s64 a, s64 b)
 	return res > a;
 }
 
+static bool check_reg_sane_offset(struct bpf_verifier_env *env,
+				  const struct bpf_reg_state *reg,
+				  enum bpf_reg_type type)
+{
+	bool known = tnum_is_const(reg->var_off);
+	s64 val = reg->var_off.value;
+	s64 smin = reg->smin_value;
+
+	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);
+		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);
+		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]);
+		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]);
+		return false;
+	}
+
+	return true;
+}
+
 /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
  * Caller should also handle BPF_MOV case separately.
  * If we return -EACCES, caller may want to try again treating pointer as a
@@ -2364,29 +2424,25 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 
 	if (BPF_CLASS(insn->code) != BPF_ALU64) {
 		/* 32-bit ALU ops on pointers produce (meaningless) scalars */
-		if (!env->allow_ptr_leaks)
-			verbose(env,
-				"R%d 32-bit pointer arithmetic prohibited\n",
-				dst);
+		verbose(env,
+			"R%d 32-bit pointer arithmetic prohibited\n",
+			dst);
 		return -EACCES;
 	}
 
 	if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
-		if (!env->allow_ptr_leaks)
-			verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
-				dst);
+		verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
+			dst);
 		return -EACCES;
 	}
 	if (ptr_reg->type == CONST_PTR_TO_MAP) {
-		if (!env->allow_ptr_leaks)
-			verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
-				dst);
+		verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
+			dst);
 		return -EACCES;
 	}
 	if (ptr_reg->type == PTR_TO_PACKET_END) {
-		if (!env->allow_ptr_leaks)
-			verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
-				dst);
+		verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
+			dst);
 		return -EACCES;
 	}
 
@@ -2396,6 +2452,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	dst_reg->type = ptr_reg->type;
 	dst_reg->id = ptr_reg->id;
 
+	if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) ||
+	    !check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
+		return -EINVAL;
+
 	switch (opcode) {
 	case BPF_ADD:
 		/* We can take a fixed offset as long as it doesn't overflow
@@ -2449,9 +2509,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	case BPF_SUB:
 		if (dst_reg == off_reg) {
 			/* scalar -= pointer.  Creates an unknown scalar */
-			if (!env->allow_ptr_leaks)
-				verbose(env, "R%d tried to subtract pointer from scalar\n",
-					dst);
+			verbose(env, "R%d tried to subtract pointer from scalar\n",
+				dst);
 			return -EACCES;
 		}
 		/* We don't allow subtraction from FP, because (according to
@@ -2459,9 +2518,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		 * be able to deal with it.
 		 */
 		if (ptr_reg->type == PTR_TO_STACK) {
-			if (!env->allow_ptr_leaks)
-				verbose(env, "R%d subtraction from stack pointer prohibited\n",
-					dst);
+			verbose(env, "R%d subtraction from stack pointer prohibited\n",
+				dst);
 			return -EACCES;
 		}
 		if (known && (ptr_reg->off - smin_val ==
@@ -2510,28 +2568,30 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	case BPF_AND:
 	case BPF_OR:
 	case BPF_XOR:
-		/* bitwise ops on pointers are troublesome, prohibit for now.
-		 * (However, in principle we could allow some cases, e.g.
-		 * ptr &= ~3 which would reduce min_value by 3.)
-		 */
-		if (!env->allow_ptr_leaks)
-			verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
-				dst, bpf_alu_string[opcode >> 4]);
+		/* bitwise ops on pointers are troublesome, prohibit. */
+		verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
+			dst, bpf_alu_string[opcode >> 4]);
 		return -EACCES;
 	default:
 		/* other operators (e.g. MUL,LSH) produce non-pointer results */
-		if (!env->allow_ptr_leaks)
-			verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
-				dst, bpf_alu_string[opcode >> 4]);
+		verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
+			dst, bpf_alu_string[opcode >> 4]);
 		return -EACCES;
 	}
 
+	if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
+		return -EINVAL;
+
 	__update_reg_bounds(dst_reg);
 	__reg_deduce_bounds(dst_reg);
 	__reg_bound_offset(dst_reg);
 	return 0;
 }
 
+/* WARNING: This function does calculations on 64-bit values, but the actual
+ * execution may occur on 32-bit values. Therefore, things like bitshifts
+ * need extra checks in the 32-bit case.
+ */
 static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 				      struct bpf_insn *insn,
 				      struct bpf_reg_state *dst_reg,
@@ -2542,12 +2602,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	bool src_known, dst_known;
 	s64 smin_val, smax_val;
 	u64 umin_val, umax_val;
+	u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
 
-	if (BPF_CLASS(insn->code) != BPF_ALU64) {
-		/* 32-bit ALU ops are (32,32)->64 */
-		coerce_reg_to_32(dst_reg);
-		coerce_reg_to_32(&src_reg);
-	}
 	smin_val = src_reg.smin_value;
 	smax_val = src_reg.smax_value;
 	umin_val = src_reg.umin_value;
@@ -2555,6 +2611,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	src_known = tnum_is_const(src_reg.var_off);
 	dst_known = tnum_is_const(dst_reg->var_off);
 
+	if (!src_known &&
+	    opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
+		__mark_reg_unknown(dst_reg);
+		return 0;
+	}
+
 	switch (opcode) {
 	case BPF_ADD:
 		if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
@@ -2683,9 +2745,9 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		__update_reg_bounds(dst_reg);
 		break;
 	case BPF_LSH:
-		if (umax_val > 63) {
-			/* Shifts greater than 63 are undefined.  This includes
-			 * shifts by a negative number.
+		if (umax_val >= insn_bitness) {
+			/* Shifts greater than 31 or 63 are undefined.
+			 * This includes shifts by a negative number.
 			 */
 			mark_reg_unknown(env, regs, insn->dst_reg);
 			break;
@@ -2711,27 +2773,29 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		__update_reg_bounds(dst_reg);
 		break;
 	case BPF_RSH:
-		if (umax_val > 63) {
-			/* Shifts greater than 63 are undefined.  This includes
-			 * shifts by a negative number.
+		if (umax_val >= insn_bitness) {
+			/* Shifts greater than 31 or 63 are undefined.
+			 * This includes shifts by a negative number.
 			 */
 			mark_reg_unknown(env, regs, insn->dst_reg);
 			break;
 		}
-		/* BPF_RSH is an unsigned shift, so make the appropriate casts */
-		if (dst_reg->smin_value < 0) {
-			if (umin_val) {
-				/* Sign bit will be cleared */
-				dst_reg->smin_value = 0;
-			} else {
-				/* Lost sign bit information */
-				dst_reg->smin_value = S64_MIN;
-				dst_reg->smax_value = S64_MAX;
-			}
-		} else {
-			dst_reg->smin_value =
-				(u64)(dst_reg->smin_value) >> umax_val;
-		}
+		/* BPF_RSH is an unsigned shift.  If the value in dst_reg might
+		 * be negative, then either:
+		 * 1) src_reg might be zero, so the sign bit of the result is
+		 *    unknown, so we lose our signed bounds
+		 * 2) it's known negative, thus the unsigned bounds capture the
+		 *    signed bounds
+		 * 3) the signed bounds cross zero, so they tell us nothing
+		 *    about the result
+		 * If the value in dst_reg is known nonnegative, then again the
+		 * unsigned bounts capture the signed bounds.
+		 * Thus, in all cases it suffices to blow away our signed bounds
+		 * and rely on inferring new ones from the unsigned bounds and
+		 * var_off of the result.
+		 */
+		dst_reg->smin_value = S64_MIN;
+		dst_reg->smax_value = S64_MAX;
 		if (src_known)
 			dst_reg->var_off = tnum_rshift(dst_reg->var_off,
 						       umin_val);
@@ -2747,6 +2811,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		break;
 	}
 
+	if (BPF_CLASS(insn->code) != BPF_ALU64) {
+		/* 32-bit ALU ops are (32,32)->32 */
+		coerce_reg_to_size(dst_reg, 4);
+		coerce_reg_to_size(&src_reg, 4);
+	}
+
 	__reg_deduce_bounds(dst_reg);
 	__reg_bound_offset(dst_reg);
 	return 0;
@@ -2763,7 +2833,6 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
 	struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
 	u8 opcode = BPF_OP(insn->code);
-	int rc;
 
 	dst_reg = &regs[insn->dst_reg];
 	src_reg = NULL;
@@ -2774,43 +2843,29 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		if (src_reg->type != SCALAR_VALUE) {
 			if (dst_reg->type != SCALAR_VALUE) {
 				/* Combining two pointers by any ALU op yields
-				 * an arbitrary scalar.
+				 * an arbitrary scalar. Disallow all math except
+				 * pointer subtraction
 				 */
-				if (!env->allow_ptr_leaks) {
-					verbose(env, "R%d pointer %s pointer prohibited\n",
-						insn->dst_reg,
-						bpf_alu_string[opcode >> 4]);
-					return -EACCES;
+				if (opcode == BPF_SUB){
+					mark_reg_unknown(env, regs, insn->dst_reg);
+					return 0;
 				}
-				mark_reg_unknown(env, regs, insn->dst_reg);
-				return 0;
+				verbose(env, "R%d pointer %s pointer prohibited\n",
+					insn->dst_reg,
+					bpf_alu_string[opcode >> 4]);
+				return -EACCES;
 			} else {
 				/* scalar += pointer
 				 * This is legal, but we have to reverse our
 				 * src/dest handling in computing the range
 				 */
-				rc = adjust_ptr_min_max_vals(env, insn,
-							     src_reg, dst_reg);
-				if (rc == -EACCES && env->allow_ptr_leaks) {
-					/* scalar += unknown scalar */
-					__mark_reg_unknown(&off_reg);
-					return adjust_scalar_min_max_vals(
-							env, insn,
-							dst_reg, off_reg);
-				}
-				return rc;
+				return adjust_ptr_min_max_vals(env, insn,
+							       src_reg, dst_reg);
 			}
 		} else if (ptr_reg) {
 			/* pointer += scalar */
-			rc = adjust_ptr_min_max_vals(env, insn,
-						     dst_reg, src_reg);
-			if (rc == -EACCES && env->allow_ptr_leaks) {
-				/* unknown scalar += scalar */
-				__mark_reg_unknown(dst_reg);
-				return adjust_scalar_min_max_vals(
-						env, insn, dst_reg, *src_reg);
-			}
-			return rc;
+			return adjust_ptr_min_max_vals(env, insn,
+						       dst_reg, src_reg);
 		}
 	} else {
 		/* Pretend the src is a reg with a known value, since we only
@@ -2819,17 +2874,9 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		off_reg.type = SCALAR_VALUE;
 		__mark_reg_known(&off_reg, insn->imm);
 		src_reg = &off_reg;
-		if (ptr_reg) { /* pointer += K */
-			rc = adjust_ptr_min_max_vals(env, insn,
-						     ptr_reg, src_reg);
-			if (rc == -EACCES && env->allow_ptr_leaks) {
-				/* unknown scalar += K */
-				__mark_reg_unknown(dst_reg);
-				return adjust_scalar_min_max_vals(
-						env, insn, dst_reg, off_reg);
-			}
-			return rc;
-		}
+		if (ptr_reg) /* pointer += K */
+			return adjust_ptr_min_max_vals(env, insn,
+						       ptr_reg, src_reg);
 	}
 
 	/* Got here implies adding two SCALAR_VALUEs */
@@ -2926,17 +2973,20 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 					return -EACCES;
 				}
 				mark_reg_unknown(env, regs, insn->dst_reg);
-				/* high 32 bits are known zero. */
-				regs[insn->dst_reg].var_off = tnum_cast(
-						regs[insn->dst_reg].var_off, 4);
-				__update_reg_bounds(&regs[insn->dst_reg]);
+				coerce_reg_to_size(&regs[insn->dst_reg], 4);
 			}
 		} else {
 			/* case: R = imm
 			 * remember the value we stored into this reg
 			 */
 			regs[insn->dst_reg].type = SCALAR_VALUE;
-			__mark_reg_known(regs + insn->dst_reg, insn->imm);
+			if (BPF_CLASS(insn->code) == BPF_ALU64) {
+				__mark_reg_known(regs + insn->dst_reg,
+						 insn->imm);
+			} else {
+				__mark_reg_known(regs + insn->dst_reg,
+						 (u32)insn->imm);
+			}
 		}
 
 	} else if (opcode > BPF_END) {
@@ -4013,15 +4063,14 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
 			return range_within(rold, rcur) &&
 			       tnum_in(rold->var_off, rcur->var_off);
 		} else {
-			/* if we knew anything about the old value, we're not
-			 * equal, because we can't know anything about the
-			 * scalar value of the pointer in the new value.
+			/* We're trying to use a pointer in place of a scalar.
+			 * Even if the scalar was unbounded, this could lead to
+			 * pointer leaks because scalars are allowed to leak
+			 * while pointers are not. We could make this safe in
+			 * special cases if root is calling us, but it's
+			 * probably not worth the hassle.
 			 */
-			return rold->umin_value == 0 &&
-			       rold->umax_value == U64_MAX &&
-			       rold->smin_value == S64_MIN &&
-			       rold->smax_value == S64_MAX &&
-			       tnum_is_unknown(rold->var_off);
+			return false;
 		}
 	case PTR_TO_MAP_VALUE:
 		/* If the new min/max/var_off satisfy the old ones and
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 13d6881f908b..ec999f32c840 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -434,17 +434,22 @@ static struct pid *good_sigevent(sigevent_t * event)
 {
 	struct task_struct *rtn = current->group_leader;
 
-	if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
-		(!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
-		 !same_thread_group(rtn, current) ||
-		 (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL))
+	switch (event->sigev_notify) {
+	case SIGEV_SIGNAL | SIGEV_THREAD_ID:
+		rtn = find_task_by_vpid(event->sigev_notify_thread_id);
+		if (!rtn || !same_thread_group(rtn, current))
+			return NULL;
+		/* FALLTHRU */
+	case SIGEV_SIGNAL:
+	case SIGEV_THREAD:
+		if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX)
+			return NULL;
+		/* FALLTHRU */
+	case SIGEV_NONE:
+		return task_pid(rtn);
+	default:
 		return NULL;
-
-	if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
-	    ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
-		return NULL;
-
-	return task_pid(rtn);
+	}
 }
 
 static struct k_itimer * alloc_posix_timer(void)
@@ -669,7 +674,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 	struct timespec64 ts64;
 	bool sig_none;
 
-	sig_none = (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE;
+	sig_none = timr->it_sigev_notify == SIGEV_NONE;
 	iv = timr->it_interval;
 
 	/* interval timer ? */
@@ -856,7 +861,7 @@ int common_timer_set(struct k_itimer *timr, int flags,
 
 	timr->it_interval = timespec64_to_ktime(new_setting->it_interval);
 	expires = timespec64_to_ktime(new_setting->it_value);
-	sigev_none = (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE;
+	sigev_none = timr->it_sigev_notify == SIGEV_NONE;
 
 	kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none);
 	timr->it_active = !sigev_none;