[RFC PATCH net-next v2 05/17] ethtool: netlink bitset handling

@@ -59,6 +59,62 @@ provided by kernel. In dump requests, device is not specified and kernel
 replies with one message per network device (only those for which the request
 is supported).
 
+Bit sets
+--------
+
+For short bitmaps of (reasonably) fixed length, standard NLA_BITFIELD32 type
+is used. For arbitrary length bitmaps, ethtool netlink uses a nested attribute
+with contents of one of two forms: compact (two binary bitmaps representing
+bit values and mask of affected bits) and bit-by-bit (list of bits identified
+by either index or name).
+
+Compact form: nested (bitset) atrribute contents:
+
+    ETHA_BITSET_SIZE	(u32)		number of significant bits
+    ETHA_BITSET_VALUE	(binary)	bitmap of bit values
+    ETHA_BITSET_MASK	(binary)	bitmap of valid bits
+
+Value and mask must have length at least ETHA_BITSET_SIZE bits rounded up to
+a multiple of 32 bits. They consist of 32-bit words in host byt order, words
+ordered from least significant to most significant (i.e. the same way as
+bitmaps are passed with ioctl interface).
+
+For compact form, ETHA_BITSET_SIZE and ETHA_BITSET_VALUE are mandatory.
+Similar to BITFIELD32, a compact form bit set requests to set bits in the mask
+to 1 (if set in value) or 0 (if not) and preserve the rest. If the mask is
+omitted, it is supposed to be "all ones", i.e. set all bits according to
+value.
+
+Kernel bit set length may differ from userspace length if older application is
+used on newer kernel or vice versa. If userspace bitmaps are longer, error is
+only issued if request actually tries to set bits not implemented in kernel.
+
+Bit-by-bit form: nested (bitset) attribute contents:
+
+    ETHA_BITSET_SIZE	(u32)		number of significant bits (optional)
+    ETHA_BITSET_BITS	(nested)	array of bits
+	ETHA_BITSET_BIT
+	    ETHA_BIT_INDEX	(u32)		bit index (0 for LSB)
+            ETHA_BIT_NAME	(string)	bit name
+	    ETHA_BIT_VALUE	(flag)		present if bit is set
+        ETHA_BITSET_BIT
+	...
+
+Bit size is optional for bit-by-bit form. ETHA_BITSET_BITS nest can only
+contain ETHA_BITS_BIT attributes but there can be an arbitrary number of them.
+A bit may be identified by its index or by its name. When used in requests,
+listed bits are set to 0 or 1 according to ETHA_BIT_VALUE, the rest is
+preserved. A request fails if index exceeds kernel bit length or if name is
+not recognized.
+
+In requests, application can use either form. Form used by kernel in reply is
+determined by a flag in flags field of request header. Semantics of value and
+mask depends on the attribute. General idea is that flags control request
+processing, info_mask control which parts of the information are returned in
+"get" request and index identifies a particular subcommand or an object to
+which the request applies.
+
+
 List of message types
 ---------------------
 

@@ -23,6 +23,37 @@ enum {
 	ETHA_DEV_MAX = (__ETHA_DEV_MAX - 1)
 };
 
+/* bit sets */
+
+enum {
+	ETHA_BIT_UNSPEC,
+	ETHA_BIT_INDEX,				/* u32 */
+	ETHA_BIT_NAME,				/* string */
+	ETHA_BIT_VALUE,				/* flag */
+
+	__ETHA_BIT_MAX,
+	ETHA_BIT_MAX = (__ETHA_BIT_MAX - 1)
+};
+
+enum {
+	ETHA_BITS_UNSPEC,
+	ETHA_BITS_BIT,
+
+	__ETHA_BITS_MAX,
+	ETHA_BITS_MAX = (__ETHA_BITS_MAX - 1)
+};
+
+enum {
+	ETHA_BITSET_UNSPEC,
+	ETHA_BITSET_SIZE,			/* u32 */
+	ETHA_BITSET_BITS,			/* nest - ETHA_BITS_* */
+	ETHA_BITSET_VALUE,			/* binary */
+	ETHA_BITSET_MASK,			/* binary */
+
+	__ETHA_BITSET_MAX,
+	ETHA_BITSET_MAX = (__ETHA_BITSET_MAX - 1)
+};
+
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1

@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 
 #include <linux/module.h>
+#include <linux/bitmap.h>
 #include <net/sock.h>
 #include <linux/ethtool_netlink.h>
 #include "netlink.h"

@@ -67,6 +68,400 @@ int ethnl_fill_dev(struct sk_buff *msg, struct net_device *dev, u16 attrtype)
 	return ret;
 }
 
+/* bitset helper functions */
+
+static bool ethnl_test_bit(u32 *val, unsigned int index)
+{
+	if (val)
+		return val[index / 32] & (1 << (index % 32));
+	else
+		return true;
+}
+
+static void ethnl_copy_bitmap(u32 *dst, u32 *src, unsigned int size)
+{
+	unsigned int full_words = size / 32;
+
+	memcpy(dst, src, full_words * sizeof(u32));
+	if (size % 32 != 0)
+		dst[full_words] = src[full_words] & ((1U << (size % 32)) - 1);
+}
+
+static void ethnl_fill_bitmap(u32 *dst, unsigned int size)
+{
+	unsigned int full_words = size / 32;
+
+	memset(dst, 0xff, full_words * sizeof(u32));
+	if (size % 32 != 0)
+		dst[full_words] = (1U << (size % 32)) - 1;
+}
+
+/* convert standard kernel bitmap (long sized words) to ethtool one (u32 words)
+ * bitmap_to_arr32() is not guaranteed to do "in place" conversion correctly;
+ * moreover, we can use the fact that the conversion is no-op except for 64-bit
+ * big endian architectures
+ */
+#if BITS_PER_LONG == 64 && defined(__BIG_ENDIAN)
+void ethnl_bitmap_to_u32(unsigned long *bitmap, unsigned int nwords)
+{
+	u32 *dst = (u32 *)bitmap;
+	unsigned int i;
+
+	for (i = 0; i < nwords; i++) {
+		unsigned long tmp = READ_ONCE(bitmap[i]);
+
+		dst[2 * i] = tmp & 0xffffffff;
+		dst[2 * i + 1] = tmp >> 32;
+	}
+}
+#endif
+
+/* calculate size for a bitset attribute
+ * see ethnl_put_bitset() for arguments
+ */
+int ethnl_bitset32_size(bool compact, unsigned int size, u32 *val, u32 *mask,
+			const char *const *names)
+{
+	unsigned int nwords = (size + 31) / 32;
+	unsigned int len;
+
+	if (WARN_ON(!compact && !names))
+		return -EINVAL;
+	/* size */
+	len = nla_total_size(sizeof(u32));
+
+	if (compact) {
+		/* values, mask */
+		len += 2 * nla_total_size(nwords * sizeof(u32));
+	} else {
+		unsigned int bits_len = 0;
+		unsigned int bit_len, i;
+
+		for (i = 0; i < size; i++) {
+			if (!ethnl_test_bit(mask, i))
+				continue;
+			/* index */
+			bit_len = nla_total_size(sizeof(u32));
+			/* name */
+			bit_len += ethnl_str_size(names[i] ?: "");
+			/* value */
+			if (ethnl_test_bit(val, i))
+				bit_len += nla_total_size(0);
+
+			/* bit nest */
+			bits_len += nla_total_size(bit_len);
+		}
+		len += nla_total_size(bits_len);
+	}
+
+	/* outermost nest */
+	return nla_total_size(len);
+}
+
+int ethnl_bitset_size(bool compact, unsigned int size, unsigned long *val,
+		      unsigned long *mask, const char *const *names)
+{
+	const unsigned int words = (size + 31) / 32;
+	u32 mask32[words];
+	u32 val32[words];
+	int ret;
+
+	bitmap_to_arr32(val32, val, size);
+	if (mask)
+		bitmap_to_arr32(mask32, mask, size);
+	ret = ethnl_bitset32_size(compact, size, val32, mask ? mask32 : NULL,
+				  names);
+	bitmap_from_arr32(val, val32, size);
+	if (mask)
+		bitmap_from_arr32(mask, mask32, size);
+
+	return ret;
+}
+
+/* put bitset into a message
+ * skb:      skb with the message
+ * attrtype: attribute type for the bitset
+ * compact:  compact (bitmaps) or verbose (bit-by-bit with names) format
+ * size:     size of the set in bits
+ * val:      bitset values
+ * mask:     mask of valid bits
+ * names:    bit names (only used for verbose format)
+ */
+int ethnl_put_bitset32(struct sk_buff *skb, int attrtype, bool compact,
+		       unsigned int size, u32 *val, u32 *mask,
+		       const char *const *names)
+{
+	struct nlattr *nest;
+	struct nlattr *attr;
+	int ret;
+
+	if (WARN_ON(!compact && !names))
+		return -EINVAL;
+	nest = ethnl_nest_start(skb, attrtype);
+	if (!nest)
+		return -EMSGSIZE;
+
+	ret = -EMSGSIZE;
+	if (nla_put_u32(skb, ETHA_BITSET_SIZE, size))
+		goto err;
+	if (compact) {
+		unsigned int bytesize = ((size + 31) / 32) * sizeof(u32);
+
+		ret = -EMSGSIZE;
+		attr = nla_reserve(skb, ETHA_BITSET_VALUE, bytesize);
+		if (!attr)
+			goto err;
+		ethnl_copy_bitmap(nla_data(attr), val, size);
+		attr = nla_reserve(skb, ETHA_BITSET_MASK, bytesize);
+		if (!attr)
+			goto err;
+		if (mask)
+			ethnl_copy_bitmap(nla_data(attr), mask, size);
+		else
+			ethnl_fill_bitmap(nla_data(attr), size);
+	} else {
+		struct nlattr *bits;
+		unsigned int i;
+
+		bits = ethnl_nest_start(skb, ETHA_BITSET_BITS);
+		if (!bits)
+			goto err;
+		for (i = 0; i < size; i++) {
+			if (!ethnl_test_bit(mask, i))
+				continue;
+			attr = ethnl_nest_start(skb, ETHA_BITS_BIT);
+			if (!attr ||
+			    nla_put_u32(skb, ETHA_BIT_INDEX, i) ||
+			    nla_put_string(skb, ETHA_BIT_NAME, names[i] ?: ""))
+				goto err;
+			if (ethnl_test_bit(val, i))
+				if (nla_put_flag(skb, ETHA_BIT_VALUE))
+					goto err;
+			nla_nest_end(skb, attr);
+		}
+		nla_nest_end(skb, bits);
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+err:
+	nla_nest_cancel(skb, nest);
+	return ret;
+}
+
+int ethnl_put_bitset(struct sk_buff *skb, int attrtype, bool compact,
+		     unsigned int size, unsigned long *val, unsigned long *mask,
+		     const char *const *names)
+{
+	const unsigned int words = (size + 31) / 32;
+	u32 mask32[words];
+	u32 val32[words];
+	int ret;
+
+	bitmap_to_arr32(val32, val, size);
+	if (mask)
+		bitmap_to_arr32(mask32, mask, size);
+	ret = ethnl_put_bitset32(skb, attrtype, compact, size, val32,
+				 mask ? mask32 : NULL, names);
+	bitmap_from_arr32(val, val32, size);
+	if (mask)
+		bitmap_from_arr32(mask, mask32, size);
+
+	return ret;
+}
+
+static const struct nla_policy bitset_policy[ETHA_BITSET_MAX + 1] = {
+	[ETHA_BITSET_UNSPEC]		= { .type = NLA_UNSPEC },
+	[ETHA_BITSET_SIZE]		= { .type = NLA_U32 },
+	[ETHA_BITSET_BITS]		= { .type = NLA_NESTED },
+	[ETHA_BITSET_VALUE]		= { .type = NLA_BINARY },
+	[ETHA_BITSET_MASK]		= { .type = NLA_BINARY },
+};
+
+static const struct nla_policy bit_policy[ETHA_BIT_MAX + 1] = {
+	[ETHA_BIT_UNSPEC]		= { .type = NLA_UNSPEC },
+	[ETHA_BIT_INDEX]		= { .type = NLA_U32 },
+	[ETHA_BIT_NAME]			= { .type = NLA_STRING },
+	[ETHA_BIT_VALUE]		= { .type = NLA_FLAG },
+};
+
+static int ethnl_name_to_idx(const char *const *names, unsigned int n_names,
+			     const char *name, unsigned int name_len)
+{
+	unsigned int i;
+
+	for (i = 0; i < n_names; i++)
+		if (names[i] && !strncmp(names[i], name, name_len))
+			return i;
+
+	return n_names;
+}
+
+static int ethnl_update_bit(unsigned long *bitmap, unsigned long *bitmask,
+			    unsigned int nbits, struct nlattr *bit_attr,
+			    const char *const *names, struct genl_info *info)
+{
+	struct nlattr *tb[ETHA_BIT_MAX + 1];
+	int ret, idx;
+
+	if (nla_type(bit_attr) != ETHA_BITS_BIT) {
+		ETHNL_SET_ERRMSG(info,
+				 "ETHA_BITSET_BITS can contain only ETHA_BITS_BIT");
+		return genl_err_attr(info, -EINVAL, bit_attr);
+	}
+	ret = nla_parse_nested(tb, ETHA_BIT_MAX, bit_attr, bit_policy,
+			       info->extack);
+	if (ret < 0)
+		return ret;
+
+	if (tb[ETHA_BIT_INDEX]) {
+		idx = nla_get_u32(tb[ETHA_BIT_INDEX]);
+		if (idx >= nbits) {
+			ETHNL_SET_ERRMSG(info, "bit index too high");
+			return genl_err_attr(info, -EOPNOTSUPP,
+					     tb[ETHA_BIT_INDEX]);
+		}
+		if (tb[ETHA_BIT_NAME] && names[idx] &&
+		    strncmp(nla_data(tb[ETHA_BIT_NAME]), names[idx],
+			    nla_len(tb[ETHA_BIT_NAME]))) {
+			ETHNL_SET_ERRMSG(info, "bit index and name mismatch");
+			return genl_err_attr(info, -EINVAL, bit_attr);
+		}
+	} else if (tb[ETHA_BIT_NAME]) {
+		idx = ethnl_name_to_idx(names, nbits,
+					nla_data(tb[ETHA_BIT_NAME]),
+					nla_len(tb[ETHA_BIT_NAME]));
+		if (idx >= nbits) {
+			ETHNL_SET_ERRMSG(info, "bit name not found");
+			return genl_err_attr(info, -EOPNOTSUPP,
+					     tb[ETHA_BIT_NAME]);
+		}
+	} else {
+		ETHNL_SET_ERRMSG(info, "neither bit index nor name specified");
+		return genl_err_attr(info, -EINVAL, bit_attr);
+	}
+
+	if (tb[ETHA_BIT_VALUE])
+		set_bit(idx, bitmap);
+	else
+		clear_bit(idx, bitmap);
+	if (bitmask)
+		set_bit(idx, bitmask);
+	return 0;
+}
+
+bool ethnl_update_bitset(unsigned long *bitmap, unsigned long *bitmask,
+			 unsigned int nbits, struct nlattr *attr, int *err,
+			 const char *const *names, struct genl_info *info)
+{
+	struct nlattr *tb[ETHA_BITSET_MAX + 1];
+	unsigned int change_bits = 0;
+	bool mod = false;
+
+	if (!attr)
+		return false;
+	*err = nla_parse_nested(tb, ETHA_BITSET_MAX, attr, bitset_policy,
+				info->extack);
+	if (*err < 0)
+		return mod;
+
+	/* To let new userspace to work with old kernel, we allow bitmaps
+	 * from userspace to be longer than kernel ones and only issue an
+	 * error if userspace actually tries to change a bit not existing
+	 * in kernel.
+	 */
+	if (tb[ETHA_BITSET_SIZE])
+		change_bits = nla_get_u32(tb[ETHA_BITSET_SIZE]);
+
+	if (tb[ETHA_BITSET_BITS]) {
+		DECLARE_BITMAP(val, nbits);
+		DECLARE_BITMAP(mask, nbits);
+		struct nlattr *bit_attr;
+		int rem;
+
+		*err = -EINVAL;
+		if (tb[ETHA_BITSET_VALUE] || tb[ETHA_BITSET_MASK])
+			return mod;
+		bitmap_copy(val, bitmap, nbits);
+		bitmap_zero(mask, nbits);
+		nla_for_each_nested(bit_attr, tb[ETHA_BITSET_BITS], rem) {
+			*err = ethnl_update_bit(val, mask, nbits, bit_attr,
+						names, info);
+			if (*err < 0)
+				return mod;
+		}
+		mod = !bitmap_equal(val, bitmap, nbits);
+		if (mod)
+			bitmap_copy(bitmap, val, nbits);
+		if (bitmask)
+			bitmap_copy(bitmask, mask, nbits);
+	} else {
+		const unsigned int max_bits =
+			max_t(unsigned int, nbits, change_bits);
+		unsigned int nwords = (change_bits + 31) / 32;
+		DECLARE_BITMAP(mask, max_bits);
+		DECLARE_BITMAP(val, max_bits);
+
+		*err = -EINVAL;
+		if (!change_bits || !tb[ETHA_BITSET_VALUE])
+			return mod;
+		if (nla_len(tb[ETHA_BITSET_VALUE]) < nwords * sizeof(u32))
+			return mod;
+		if (tb[ETHA_BITSET_MASK] &&
+		    nla_len(tb[ETHA_BITSET_VALUE]) < nwords * sizeof(u32))
+			return mod;
+
+		bitmap_zero(val, max_bits);
+		bitmap_from_arr32(val, nla_data(tb[ETHA_BITSET_VALUE]),
+				  change_bits);
+		bitmap_zero(mask, max_bits);
+		if (tb[ETHA_BITSET_MASK])
+			bitmap_from_arr32(mask, nla_data(tb[ETHA_BITSET_MASK]),
+					  change_bits);
+		else
+			bitmap_fill(mask, change_bits);
+
+		if (nbits < change_bits) {
+			unsigned int idx = find_next_bit(mask, max_bits, nbits);
+
+			*err = -EINVAL;
+			if (idx >= nbits)
+				return mod;
+		}
+
+		if (bitmask)
+			bitmap_copy(bitmask, mask, nbits);
+		bitmap_and(val, val, mask, nbits);
+		bitmap_complement(mask, mask, nbits);
+		bitmap_and(mask, mask, bitmap, nbits);
+		bitmap_or(val, val, mask, nbits);
+		mod = !bitmap_equal(val, bitmap, nbits);
+		if (mod)
+			bitmap_copy(bitmap, val, nbits);
+	}
+
+	*err = 0;
+	return mod;
+}
+
+bool ethnl_update_bitset32(u32 *bitmap, u32 *bitmask, unsigned int nbits,
+			   struct nlattr *attr, int *err,
+			   const char *const *names, struct genl_info *info)
+{
+	DECLARE_BITMAP(tmp, nbits);
+	DECLARE_BITMAP(tmp_mask, nbits);
+	bool mod;
+
+	bitmap_from_arr32(tmp, bitmap, nbits);
+	bitmap_zero(tmp_mask, nbits);
+	mod = ethnl_update_bitset(tmp, tmp_mask, nbits, attr, err, names, info);
+	if (!*err && mod)
+		bitmap_to_arr32(bitmap, tmp, nbits);
+	if (bitmask)
+		bitmap_to_arr32(bitmask, tmp_mask, nbits);
+	return (!*err && mod);
+}
+
 /* create skb for a reply
  * payload: payload length (without netlink, genetlink and ethnl headers)
  * dev:     device the reply is about

@@ -20,6 +20,32 @@ struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd,
 				 u16 dev_attrtype, struct genl_info *info,
 				 void **ehdrp);
 
+#if BITS_PER_LONG == 64 && defined(__BIG_ENDIAN)
+void ethnl_bitmap_to_u32(unsigned long *bitmap, unsigned int nwords);
+#else
+static inline void ethnl_bitmap_to_u32(unsigned long *bitmap,
+				       unsigned int nwords)
+{
+}
+#endif
+
+int ethnl_bitset_size(bool compact, unsigned int size, unsigned long *val,
+		      unsigned long *mask, const char *const *names);
+int ethnl_bitset32_size(bool compact, unsigned int size, u32 *val, u32 *mask,
+			const char *const *names);
+int ethnl_put_bitset(struct sk_buff *skb, int attrtype, bool compact,
+		     unsigned int size, unsigned long *val, unsigned long *mask,
+		     const char *const *names);
+int ethnl_put_bitset32(struct sk_buff *skb, int attrtype, bool compact,
+		       unsigned int size, u32 *val, u32 *mask,
+		       const char *const *names);
+bool ethnl_update_bitset(unsigned long *bitmap, unsigned long *bitmask,
+			 unsigned int nbits, struct nlattr *attr, int *err,
+			 const char *const *names, struct genl_info *info);
+bool ethnl_update_bitset32(u32 *bitmap, u32 *bitmask, unsigned int nbits,
+			   struct nlattr *attr, int *err,
+			   const char *const *names, struct genl_info *info);
+
 static inline int ethnl_str_size(const char *s)
 {
 	return nla_total_size(strlen(s) + 1);