summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-05-08 08:03:58 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2019-05-08 08:03:58 +0300
commit80f232121b69cc69a31ccb2b38c1665d770b0710 (patch)
tree106263eac4ff03b899df695e00dd11e593e74fe2 /lib
parent82efe439599439a5e1e225ce5740e6cfb777a7dd (diff)
parenta9e41a529681b38087c91ebc0bb91e12f510ca2d (diff)
downloadlinux-80f232121b69cc69a31ccb2b38c1665d770b0710.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Highlights: 1) Support AES128-CCM ciphers in kTLS, from Vakul Garg. 2) Add fib_sync_mem to control the amount of dirty memory we allow to queue up between synchronize RCU calls, from David Ahern. 3) Make flow classifier more lockless, from Vlad Buslov. 4) Add PHY downshift support to aquantia driver, from Heiner Kallweit. 5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces contention on SLAB spinlocks in heavy RPC workloads. 6) Partial GSO offload support in XFRM, from Boris Pismenny. 7) Add fast link down support to ethtool, from Heiner Kallweit. 8) Use siphash for IP ID generator, from Eric Dumazet. 9) Pull nexthops even further out from ipv4/ipv6 routes and FIB entries, from David Ahern. 10) Move skb->xmit_more into a per-cpu variable, from Florian Westphal. 11) Improve eBPF verifier speed and increase maximum program size, from Alexei Starovoitov. 12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit spinlocks. From Neil Brown. 13) Allow tunneling with GUE encap in ipvs, from Jacky Hu. 14) Improve link partner cap detection in generic PHY code, from Heiner Kallweit. 15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan Maguire. 16) Remove SKB list implementation assumptions in SCTP, your's truly. 17) Various cleanups, optimizations, and simplifications in r8169 driver. From Heiner Kallweit. 18) Add memory accounting on TX and RX path of SCTP, from Xin Long. 19) Switch PHY drivers over to use dynamic featue detection, from Heiner Kallweit. 20) Support flow steering without masking in dpaa2-eth, from Ioana Ciocoi. 21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri Pirko. 22) Increase the strict parsing of current and future netlink attributes, also export such policies to userspace. From Johannes Berg. 23) Allow DSA tag drivers to be modular, from Andrew Lunn. 24) Remove legacy DSA probing support, also from Andrew Lunn. 25) Allow ll_temac driver to be used on non-x86 platforms, from Esben Haabendal. 26) Add a generic tracepoint for TX queue timeouts to ease debugging, from Cong Wang. 27) More indirect call optimizations, from Paolo Abeni" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits) cxgb4: Fix error path in cxgb4_init_module net: phy: improve pause mode reporting in phy_print_status dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings net: macb: Change interrupt and napi enable order in open net: ll_temac: Improve error message on error IRQ net/sched: remove block pointer from common offload structure net: ethernet: support of_get_mac_address new ERR_PTR error net: usb: smsc: fix warning reported by kbuild test robot staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check net: dsa: support of_get_mac_address new ERR_PTR error net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats vrf: sit mtu should not be updated when vrf netdev is the link net: dsa: Fix error cleanup path in dsa_init_module l2tp: Fix possible NULL pointer dereference taprio: add null check on sched_nest to avoid potential null pointer dereference net: mvpp2: cls: fix less than zero check on a u32 variable net_sched: sch_fq: handle non connected flows net_sched: sch_fq: do not assume EDT packets are ordered net: hns3: use devm_kcalloc when allocating desc_cb net: hns3: some cleanup for struct hns3_enet_ring ...
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig17
-rw-r--r--lib/Kconfig.debug8
-rw-r--r--lib/Makefile1
-rw-r--r--lib/nlattr.c200
-rw-r--r--lib/packing.c213
-rw-r--r--lib/rhashtable.c210
-rw-r--r--lib/test_rhashtable.c2
7 files changed, 458 insertions, 193 deletions
diff --git a/lib/Kconfig b/lib/Kconfig
index e86975bfca6a..f323b85ad11c 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -18,6 +18,23 @@ config RAID6_PQ_BENCHMARK
Benchmark all available RAID6 PQ functions on init and choose the
fastest one.
+config PACKING
+ bool "Generic bitfield packing and unpacking"
+ default n
+ help
+ This option provides the packing() helper function, which permits
+ converting bitfields between a CPU-usable representation and a
+ memory representation that can have any combination of these quirks:
+ - Is little endian (bytes are reversed within a 32-bit group)
+ - The least-significant 32-bit word comes first (within a 64-bit
+ group)
+ - The most significant bit of a byte is at its right (bit 0 of a
+ register description is numerically 2^7).
+ Drivers may use these helpers to match the bit indices as described
+ in the data sheets of the peripherals they are in control of.
+
+ When in doubt, say N.
+
config BITREVERSE
tristate
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 971c6c70891e..d695ec1477f3 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -219,6 +219,14 @@ config DEBUG_INFO_DWARF4
But it significantly improves the success of resolving
variables in gdb on optimized code.
+config DEBUG_INFO_BTF
+ bool "Generate BTF typeinfo"
+ depends on DEBUG_INFO
+ help
+ Generate deduplicated BTF type information from DWARF debug info.
+ Turning this on expects presence of pahole tool, which will convert
+ DWARF type info into equivalent deduplicated BTF type info.
+
config GDB_SCRIPTS
bool "Provide GDB scripts for kernel debugging"
depends on DEBUG_INFO
diff --git a/lib/Makefile b/lib/Makefile
index 07506e3891a0..83d7df2661ff 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -120,6 +120,7 @@ obj-$(CONFIG_DEBUG_LIST) += list_debug.o
obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
obj-$(CONFIG_BITREVERSE) += bitrev.o
+obj-$(CONFIG_PACKING) += packing.o
obj-$(CONFIG_RATIONAL) += rational.o
obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
obj-$(CONFIG_CRC16) += crc16.o
diff --git a/lib/nlattr.c b/lib/nlattr.c
index d26de6156b97..cace9b307781 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -69,7 +69,8 @@ static int validate_nla_bitfield32(const struct nlattr *nla,
static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
const struct nla_policy *policy,
- struct netlink_ext_ack *extack)
+ struct netlink_ext_ack *extack,
+ unsigned int validate)
{
const struct nlattr *entry;
int rem;
@@ -86,8 +87,8 @@ static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
return -ERANGE;
}
- ret = nla_validate(nla_data(entry), nla_len(entry),
- maxtype, policy, extack);
+ ret = __nla_validate(nla_data(entry), nla_len(entry),
+ maxtype, policy, validate, extack);
if (ret < 0)
return ret;
}
@@ -154,13 +155,17 @@ static int nla_validate_int_range(const struct nla_policy *pt,
}
static int validate_nla(const struct nlattr *nla, int maxtype,
- const struct nla_policy *policy,
+ const struct nla_policy *policy, unsigned int validate,
struct netlink_ext_ack *extack)
{
+ u16 strict_start_type = policy[0].strict_start_type;
const struct nla_policy *pt;
int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla);
int err = -ERANGE;
+ if (strict_start_type && type >= strict_start_type)
+ validate |= NL_VALIDATE_STRICT;
+
if (type <= 0 || type > maxtype)
return 0;
@@ -172,6 +177,26 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
(pt->type == NLA_EXACT_LEN_WARN && attrlen != pt->len)) {
pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
current->comm, type);
+ if (validate & NL_VALIDATE_STRICT_ATTRS) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "invalid attribute length");
+ return -EINVAL;
+ }
+ }
+
+ if (validate & NL_VALIDATE_NESTED) {
+ if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) &&
+ !(nla->nla_type & NLA_F_NESTED)) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "NLA_F_NESTED is missing");
+ return -EINVAL;
+ }
+ if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY &&
+ pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "NLA_F_NESTED not expected");
+ return -EINVAL;
+ }
}
switch (pt->type) {
@@ -244,8 +269,9 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
if (attrlen < NLA_HDRLEN)
goto out_err;
if (pt->validation_data) {
- err = nla_validate(nla_data(nla), nla_len(nla), pt->len,
- pt->validation_data, extack);
+ err = __nla_validate(nla_data(nla), nla_len(nla), pt->len,
+ pt->validation_data, validate,
+ extack);
if (err < 0) {
/*
* return directly to preserve the inner
@@ -268,7 +294,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
err = nla_validate_array(nla_data(nla), nla_len(nla),
pt->len, pt->validation_data,
- extack);
+ extack, validate);
if (err < 0) {
/*
* return directly to preserve the inner
@@ -278,10 +304,23 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
}
}
break;
+
+ case NLA_UNSPEC:
+ if (validate & NL_VALIDATE_UNSPEC) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "Unsupported attribute");
+ return -EINVAL;
+ }
+ /* fall through */
+ case NLA_MIN_LEN:
+ if (attrlen < pt->len)
+ goto out_err;
+ break;
+
default:
if (pt->len)
minlen = pt->len;
- else if (pt->type != NLA_UNSPEC)
+ else
minlen = nla_attr_minlen[pt->type];
if (attrlen < minlen)
@@ -315,37 +354,76 @@ out_err:
return err;
}
+static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
+ const struct nla_policy *policy,
+ unsigned int validate,
+ struct netlink_ext_ack *extack,
+ struct nlattr **tb)
+{
+ const struct nlattr *nla;
+ int rem;
+
+ if (tb)
+ memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+
+ nla_for_each_attr(nla, head, len, rem) {
+ u16 type = nla_type(nla);
+
+ if (type == 0 || type > maxtype) {
+ if (validate & NL_VALIDATE_MAXTYPE) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "Unknown attribute type");
+ return -EINVAL;
+ }
+ continue;
+ }
+ if (policy) {
+ int err = validate_nla(nla, maxtype, policy,
+ validate, extack);
+
+ if (err < 0)
+ return err;
+ }
+
+ if (tb)
+ tb[type] = (struct nlattr *)nla;
+ }
+
+ if (unlikely(rem > 0)) {
+ pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
+ rem, current->comm);
+ NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes");
+ if (validate & NL_VALIDATE_TRAILING)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
/**
- * nla_validate - Validate a stream of attributes
+ * __nla_validate - Validate a stream of attributes
* @head: head of attribute stream
* @len: length of attribute stream
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
+ * @validate: validation strictness
* @extack: extended ACK report struct
*
* Validates all attributes in the specified attribute stream against the
- * specified policy. Attributes with a type exceeding maxtype will be
- * ignored. See documenation of struct nla_policy for more details.
+ * specified policy. Validation depends on the validate flags passed, see
+ * &enum netlink_validation for more details on that.
+ * See documenation of struct nla_policy for more details.
*
* Returns 0 on success or a negative error code.
*/
-int nla_validate(const struct nlattr *head, int len, int maxtype,
- const struct nla_policy *policy,
- struct netlink_ext_ack *extack)
+int __nla_validate(const struct nlattr *head, int len, int maxtype,
+ const struct nla_policy *policy, unsigned int validate,
+ struct netlink_ext_ack *extack)
{
- const struct nlattr *nla;
- int rem;
-
- nla_for_each_attr(nla, head, len, rem) {
- int err = validate_nla(nla, maxtype, policy, extack);
-
- if (err < 0)
- return err;
- }
-
- return 0;
+ return __nla_validate_parse(head, len, maxtype, policy, validate,
+ extack, NULL);
}
-EXPORT_SYMBOL(nla_validate);
+EXPORT_SYMBOL(__nla_validate);
/**
* nla_policy_len - Determin the max. length of a policy
@@ -377,76 +455,30 @@ nla_policy_len(const struct nla_policy *p, int n)
EXPORT_SYMBOL(nla_policy_len);
/**
- * nla_parse - Parse a stream of attributes into a tb buffer
+ * __nla_parse - Parse a stream of attributes into a tb buffer
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @head: head of attribute stream
* @len: length of attribute stream
* @policy: validation policy
+ * @validate: validation strictness
+ * @extack: extended ACK pointer
*
* Parses a stream of attributes and stores a pointer to each attribute in
- * the tb array accessible via the attribute type. Attributes with a type
- * exceeding maxtype will be silently ignored for backwards compatibility
- * reasons. policy may be set to NULL if no validation is required.
+ * the tb array accessible via the attribute type.
+ * Validation is controlled by the @validate parameter.
*
* Returns 0 on success or a negative error code.
*/
-static int __nla_parse(struct nlattr **tb, int maxtype,
- const struct nlattr *head, int len,
- bool strict, const struct nla_policy *policy,
- struct netlink_ext_ack *extack)
-{
- const struct nlattr *nla;
- int rem;
-
- memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
-
- nla_for_each_attr(nla, head, len, rem) {
- u16 type = nla_type(nla);
-
- if (type == 0 || type > maxtype) {
- if (strict) {
- NL_SET_ERR_MSG(extack, "Unknown attribute type");
- return -EINVAL;
- }
- continue;
- }
- if (policy) {
- int err = validate_nla(nla, maxtype, policy, extack);
-
- if (err < 0)
- return err;
- }
-
- tb[type] = (struct nlattr *)nla;
- }
-
- if (unlikely(rem > 0)) {
- pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
- rem, current->comm);
- NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes");
- if (strict)
- return -EINVAL;
- }
-
- return 0;
-}
-
-int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
- int len, const struct nla_policy *policy,
- struct netlink_ext_ack *extack)
-{
- return __nla_parse(tb, maxtype, head, len, false, policy, extack);
-}
-EXPORT_SYMBOL(nla_parse);
-
-int nla_parse_strict(struct nlattr **tb, int maxtype, const struct nlattr *head,
- int len, const struct nla_policy *policy,
- struct netlink_ext_ack *extack)
+int __nla_parse(struct nlattr **tb, int maxtype,
+ const struct nlattr *head, int len,
+ const struct nla_policy *policy, unsigned int validate,
+ struct netlink_ext_ack *extack)
{
- return __nla_parse(tb, maxtype, head, len, true, policy, extack);
+ return __nla_validate_parse(head, len, maxtype, policy, validate,
+ extack, tb);
}
-EXPORT_SYMBOL(nla_parse_strict);
+EXPORT_SYMBOL(__nla_parse);
/**
* nla_find - Find a specific attribute in a stream of attributes
diff --git a/lib/packing.c b/lib/packing.c
new file mode 100644
index 000000000000..50d1e9f2f5a7
--- /dev/null
+++ b/lib/packing.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#include <linux/packing.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+static int get_le_offset(int offset)
+{
+ int closest_multiple_of_4;
+
+ closest_multiple_of_4 = (offset / 4) * 4;
+ offset -= closest_multiple_of_4;
+ return closest_multiple_of_4 + (3 - offset);
+}
+
+static int get_reverse_lsw32_offset(int offset, size_t len)
+{
+ int closest_multiple_of_4;
+ int word_index;
+
+ word_index = offset / 4;
+ closest_multiple_of_4 = word_index * 4;
+ offset -= closest_multiple_of_4;
+ word_index = (len / 4) - word_index - 1;
+ return word_index * 4 + offset;
+}
+
+static u64 bit_reverse(u64 val, unsigned int width)
+{
+ u64 new_val = 0;
+ unsigned int bit;
+ unsigned int i;
+
+ for (i = 0; i < width; i++) {
+ bit = (val & (1 << i)) != 0;
+ new_val |= (bit << (width - i - 1));
+ }
+ return new_val;
+}
+
+static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit,
+ int *box_end_bit, u8 *box_mask)
+{
+ int box_bit_width = *box_start_bit - *box_end_bit + 1;
+ int new_box_start_bit, new_box_end_bit;
+
+ *to_write >>= *box_end_bit;
+ *to_write = bit_reverse(*to_write, box_bit_width);
+ *to_write <<= *box_end_bit;
+
+ new_box_end_bit = box_bit_width - *box_start_bit - 1;
+ new_box_start_bit = box_bit_width - *box_end_bit - 1;
+ *box_mask = GENMASK_ULL(new_box_start_bit, new_box_end_bit);
+ *box_start_bit = new_box_start_bit;
+ *box_end_bit = new_box_end_bit;
+}
+
+/**
+ * packing - Convert numbers (currently u64) between a packed and an unpacked
+ * format. Unpacked means laid out in memory in the CPU's native
+ * understanding of integers, while packed means anything else that
+ * requires translation.
+ *
+ * @pbuf: Pointer to a buffer holding the packed value.
+ * @uval: Pointer to an u64 holding the unpacked value.
+ * @startbit: The index (in logical notation, compensated for quirks) where
+ * the packed value starts within pbuf. Must be larger than, or
+ * equal to, endbit.
+ * @endbit: The index (in logical notation, compensated for quirks) where
+ * the packed value ends within pbuf. Must be smaller than, or equal
+ * to, startbit.
+ * @op: If PACK, then uval will be treated as const pointer and copied (packed)
+ * into pbuf, between startbit and endbit.
+ * If UNPACK, then pbuf will be treated as const pointer and the logical
+ * value between startbit and endbit will be copied (unpacked) to uval.
+ * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
+ * QUIRK_MSB_ON_THE_RIGHT.
+ *
+ * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
+ * correct usage, return code may be discarded.
+ * If op is PACK, pbuf is modified.
+ * If op is UNPACK, uval is modified.
+ */
+int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen,
+ enum packing_op op, u8 quirks)
+{
+ /* Number of bits for storing "uval"
+ * also width of the field to access in the pbuf
+ */
+ u64 value_width;
+ /* Logical byte indices corresponding to the
+ * start and end of the field.
+ */
+ int plogical_first_u8, plogical_last_u8, box;
+
+ /* startbit is expected to be larger than endbit */
+ if (startbit < endbit)
+ /* Invalid function call */
+ return -EINVAL;
+
+ value_width = startbit - endbit + 1;
+ if (value_width > 64)
+ return -ERANGE;
+
+ /* Check if "uval" fits in "value_width" bits.
+ * If value_width is 64, the check will fail, but any
+ * 64-bit uval will surely fit.
+ */
+ if (op == PACK && value_width < 64 && (*uval >= (1ull << value_width)))
+ /* Cannot store "uval" inside "value_width" bits.
+ * Truncating "uval" is most certainly not desirable,
+ * so simply erroring out is appropriate.
+ */
+ return -ERANGE;
+
+ /* Initialize parameter */
+ if (op == UNPACK)
+ *uval = 0;
+
+ /* Iterate through an idealistic view of the pbuf as an u64 with
+ * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low
+ * logical bit significance. "box" denotes the current logical u8.
+ */
+ plogical_first_u8 = startbit / 8;
+ plogical_last_u8 = endbit / 8;
+
+ for (box = plogical_first_u8; box >= plogical_last_u8; box--) {
+ /* Bit indices into the currently accessed 8-bit box */
+ int box_start_bit, box_end_bit, box_addr;
+ u8 box_mask;
+ /* Corresponding bits from the unpacked u64 parameter */
+ int proj_start_bit, proj_end_bit;
+ u64 proj_mask;
+
+ /* This u8 may need to be accessed in its entirety
+ * (from bit 7 to bit 0), or not, depending on the
+ * input arguments startbit and endbit.
+ */
+ if (box == plogical_first_u8)
+ box_start_bit = startbit % 8;
+ else
+ box_start_bit = 7;
+ if (box == plogical_last_u8)
+ box_end_bit = endbit % 8;
+ else
+ box_end_bit = 0;
+
+ /* We have determined the box bit start and end.
+ * Now we calculate where this (masked) u8 box would fit
+ * in the unpacked (CPU-readable) u64 - the u8 box's
+ * projection onto the unpacked u64. Though the
+ * box is u8, the projection is u64 because it may fall
+ * anywhere within the unpacked u64.
+ */
+ proj_start_bit = ((box * 8) + box_start_bit) - endbit;
+ proj_end_bit = ((box * 8) + box_end_bit) - endbit;
+ proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit);
+ box_mask = GENMASK_ULL(box_start_bit, box_end_bit);
+
+ /* Determine the offset of the u8 box inside the pbuf,
+ * adjusted for quirks. The adjusted box_addr will be used for
+ * effective addressing inside the pbuf (so it's not
+ * logical any longer).
+ */
+ box_addr = pbuflen - box - 1;
+ if (quirks & QUIRK_LITTLE_ENDIAN)
+ box_addr = get_le_offset(box_addr);
+ if (quirks & QUIRK_LSW32_IS_FIRST)
+ box_addr = get_reverse_lsw32_offset(box_addr,
+ pbuflen);
+
+ if (op == UNPACK) {
+ u64 pval;
+
+ /* Read from pbuf, write to uval */
+ pval = ((u8 *)pbuf)[box_addr] & box_mask;
+ if (quirks & QUIRK_MSB_ON_THE_RIGHT)
+ adjust_for_msb_right_quirk(&pval,
+ &box_start_bit,
+ &box_end_bit,
+ &box_mask);
+
+ pval >>= box_end_bit;
+ pval <<= proj_end_bit;
+ *uval &= ~proj_mask;
+ *uval |= pval;
+ } else {
+ u64 pval;
+
+ /* Write to pbuf, read from uval */
+ pval = (*uval) & proj_mask;
+ pval >>= proj_end_bit;
+ if (quirks & QUIRK_MSB_ON_THE_RIGHT)
+ adjust_for_msb_right_quirk(&pval,
+ &box_start_bit,
+ &box_end_bit,
+ &box_mask);
+
+ pval <<= box_end_bit;
+ ((u8 *)pbuf)[box_addr] &= ~box_mask;
+ ((u8 *)pbuf)[box_addr] |= pval;
+ }
+ }
+ return 0;
+}
+EXPORT_SYMBOL(packing);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Generic bitfield packing and unpacking");
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 97f59abc3e92..6529fe1b45c1 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -31,11 +31,10 @@
#define HASH_DEFAULT_SIZE 64UL
#define HASH_MIN_SIZE 4U
-#define BUCKET_LOCKS_PER_CPU 32UL
union nested_table {
union nested_table __rcu *table;
- struct rhash_head __rcu *bucket;
+ struct rhash_lock_head __rcu *bucket;
};
static u32 head_hashfn(struct rhashtable *ht,
@@ -56,9 +55,11 @@ EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
{
- spinlock_t *lock = rht_bucket_lock(tbl, hash);
-
- return (debug_locks) ? lockdep_is_held(lock) : 1;
+ if (!debug_locks)
+ return 1;
+ if (unlikely(tbl->nest))
+ return 1;
+ return bit_spin_is_locked(0, (unsigned long *)&tbl->buckets[hash]);
}
EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
#else
@@ -104,7 +105,6 @@ static void bucket_table_free(const struct bucket_table *tbl)
if (tbl->nest)
nested_bucket_table_free(tbl);
- free_bucket_spinlocks(tbl->locks);
kvfree(tbl);
}
@@ -131,9 +131,11 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht,
INIT_RHT_NULLS_HEAD(ntbl[i].bucket);
}
- rcu_assign_pointer(*prev, ntbl);
-
- return ntbl;
+ if (cmpxchg(prev, NULL, ntbl) == NULL)
+ return ntbl;
+ /* Raced with another thread. */
+ kfree(ntbl);
+ return rcu_dereference(*prev);
}
static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht,
@@ -169,11 +171,11 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
gfp_t gfp)
{
struct bucket_table *tbl = NULL;
- size_t size, max_locks;
+ size_t size;
int i;
+ static struct lock_class_key __key;
- size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
- tbl = kvzalloc(size, gfp);
+ tbl = kvzalloc(struct_size(tbl, buckets, nbuckets), gfp);
size = nbuckets;
@@ -185,18 +187,11 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
if (tbl == NULL)
return NULL;
- tbl->size = size;
-
- max_locks = size >> 1;
- if (tbl->nest)
- max_locks = min_t(size_t, max_locks, 1U << tbl->nest);
+ lockdep_init_map(&tbl->dep_map, "rhashtable_bucket", &__key, 0);
- if (alloc_bucket_spinlocks(&tbl->locks, &tbl->locks_mask, max_locks,
- ht->p.locks_mul, gfp) < 0) {
- bucket_table_free(tbl);
- return NULL;
- }
+ tbl->size = size;
+ rcu_head_init(&tbl->rcu);
INIT_LIST_HEAD(&tbl->walkers);
tbl->hash_rnd = get_random_u32();
@@ -220,14 +215,15 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
return new_tbl;
}
-static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
+static int rhashtable_rehash_one(struct rhashtable *ht,
+ struct rhash_lock_head __rcu **bkt,
+ unsigned int old_hash)
{
struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl);
- struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash);
int err = -EAGAIN;
struct rhash_head *head, *next, *entry;
- spinlock_t *new_bucket_lock;
+ struct rhash_head __rcu **pprev = NULL;
unsigned int new_hash;
if (new_tbl->nest)
@@ -235,7 +231,8 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
err = -ENOENT;
- rht_for_each(entry, old_tbl, old_hash) {
+ rht_for_each_from(entry, rht_ptr(bkt, old_tbl, old_hash),
+ old_tbl, old_hash) {
err = 0;
next = rht_dereference_bucket(entry->next, old_tbl, old_hash);
@@ -250,18 +247,19 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
new_hash = head_hashfn(ht, new_tbl, entry);
- new_bucket_lock = rht_bucket_lock(new_tbl, new_hash);
+ rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING);
- spin_lock_nested(new_bucket_lock, SINGLE_DEPTH_NESTING);
- head = rht_dereference_bucket(new_tbl->buckets[new_hash],
- new_tbl, new_hash);
+ head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash);
RCU_INIT_POINTER(entry->next, head);
- rcu_assign_pointer(new_tbl->buckets[new_hash], entry);
- spin_unlock(new_bucket_lock);
+ rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry);
- rcu_assign_pointer(*pprev, next);
+ if (pprev)
+ rcu_assign_pointer(*pprev, next);
+ else
+ /* Need to preserved the bit lock. */
+ rht_assign_locked(bkt, next);
out:
return err;
@@ -271,20 +269,19 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
unsigned int old_hash)
{
struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
- spinlock_t *old_bucket_lock;
+ struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
int err;
- old_bucket_lock = rht_bucket_lock(old_tbl, old_hash);
+ if (!bkt)
+ return 0;
+ rht_lock(old_tbl, bkt);
- spin_lock_bh(old_bucket_lock);
- while (!(err = rhashtable_rehash_one(ht, old_hash)))
+ while (!(err = rhashtable_rehash_one(ht, bkt, old_hash)))
;
- if (err == -ENOENT) {
- old_tbl->rehash++;
+ if (err == -ENOENT)
err = 0;
- }
- spin_unlock_bh(old_bucket_lock);
+ rht_unlock(old_tbl, bkt);
return err;
}
@@ -330,13 +327,16 @@ static int rhashtable_rehash_table(struct rhashtable *ht)
spin_lock(&ht->lock);
list_for_each_entry(walker, &old_tbl->walkers, list)
walker->tbl = NULL;
- spin_unlock(&ht->lock);
/* Wait for readers. All new readers will see the new
* table, and thus no references to the old table will
* remain.
+ * We do this inside the locked region so that
+ * rhashtable_walk_stop() can use rcu_head_after_call_rcu()
+ * to check if it should not re-link the table.
*/
call_rcu(&old_tbl->rcu, bucket_table_free_rcu);
+ spin_unlock(&ht->lock);
return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0;
}
@@ -478,6 +478,7 @@ fail:
}
static void *rhashtable_lookup_one(struct rhashtable *ht,
+ struct rhash_lock_head __rcu **bkt,
struct bucket_table *tbl, unsigned int hash,
const void *key, struct rhash_head *obj)
{
@@ -485,13 +486,12 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
.ht = ht,
.key = key,
};
- struct rhash_head __rcu **pprev;
+ struct rhash_head __rcu **pprev = NULL;
struct rhash_head *head;
int elasticity;
elasticity = RHT_ELASTICITY;
- pprev = rht_bucket_var(tbl, hash);
- rht_for_each_continue(head, *pprev, tbl, hash) {
+ rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) {
struct rhlist_head *list;
struct rhlist_head *plist;
@@ -513,7 +513,11 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
RCU_INIT_POINTER(list->next, plist);
head = rht_dereference_bucket(head->next, tbl, hash);
RCU_INIT_POINTER(list->rhead.next, head);
- rcu_assign_pointer(*pprev, obj);
+ if (pprev)
+ rcu_assign_pointer(*pprev, obj);
+ else
+ /* Need to preserve the bit lock */
+ rht_assign_locked(bkt, obj);
return NULL;
}
@@ -525,12 +529,12 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
}
static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
+ struct rhash_lock_head __rcu **bkt,
struct bucket_table *tbl,
unsigned int hash,
struct rhash_head *obj,
void *data)
{
- struct rhash_head __rcu **pprev;
struct bucket_table *new_tbl;
struct rhash_head *head;
@@ -553,11 +557,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
if (unlikely(rht_grow_above_100(ht, tbl)))
return ERR_PTR(-EAGAIN);
- pprev = rht_bucket_insert(ht, tbl, hash);
- if (!pprev)
- return ERR_PTR(-ENOMEM);
-
- head = rht_dereference_bucket(*pprev, tbl, hash);
+ head = rht_ptr(bkt, tbl, hash);
RCU_INIT_POINTER(obj->next, head);
if (ht->rhlist) {
@@ -567,7 +567,10 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
RCU_INIT_POINTER(list->next, NULL);
}
- rcu_assign_pointer(*pprev, obj);
+ /* bkt is always the head of the list, so it holds
+ * the lock, which we need to preserve
+ */
+ rht_assign_locked(bkt, obj);
atomic_inc(&ht->nelems);
if (rht_grow_above_75(ht, tbl))
@@ -581,47 +584,35 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
{
struct bucket_table *new_tbl;
struct bucket_table *tbl;
+ struct rhash_lock_head __rcu **bkt;
unsigned int hash;
- spinlock_t *lock;
void *data;
- tbl = rcu_dereference(ht->tbl);
-
- /* All insertions must grab the oldest table containing
- * the hashed bucket that is yet to be rehashed.
- */
- for (;;) {
- hash = rht_head_hashfn(ht, tbl, obj, ht->p);
- lock = rht_bucket_lock(tbl, hash);
- spin_lock_bh(lock);
-
- if (tbl->rehash <= hash)
- break;
-
- spin_unlock_bh(lock);
- tbl = rht_dereference_rcu(tbl->future_tbl, ht);
- }
-
- data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
- new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
- if (PTR_ERR(new_tbl) != -EEXIST)
- data = ERR_CAST(new_tbl);
+ new_tbl = rcu_dereference(ht->tbl);
- while (!IS_ERR_OR_NULL(new_tbl)) {
+ do {
tbl = new_tbl;
hash = rht_head_hashfn(ht, tbl, obj, ht->p);
- spin_lock_nested(rht_bucket_lock(tbl, hash),
- SINGLE_DEPTH_NESTING);
-
- data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
- new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
- if (PTR_ERR(new_tbl) != -EEXIST)
- data = ERR_CAST(new_tbl);
-
- spin_unlock(rht_bucket_lock(tbl, hash));
- }
-
- spin_unlock_bh(lock);
+ if (rcu_access_pointer(tbl->future_tbl))
+ /* Failure is OK */
+ bkt = rht_bucket_var(tbl, hash);
+ else
+ bkt = rht_bucket_insert(ht, tbl, hash);
+ if (bkt == NULL) {
+ new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+ data = ERR_PTR(-EAGAIN);
+ } else {
+ rht_lock(tbl, bkt);
+ data = rhashtable_lookup_one(ht, bkt, tbl,
+ hash, key, obj);
+ new_tbl = rhashtable_insert_one(ht, bkt, tbl,
+ hash, obj, data);
+ if (PTR_ERR(new_tbl) != -EEXIST)
+ data = ERR_CAST(new_tbl);
+
+ rht_unlock(tbl, bkt);
+ }
+ } while (!IS_ERR_OR_NULL(new_tbl));
if (PTR_ERR(data) == -EAGAIN)
data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?:
@@ -943,10 +934,11 @@ void rhashtable_walk_stop(struct rhashtable_iter *iter)
ht = iter->ht;
spin_lock(&ht->lock);
- if (tbl->rehash < tbl->size)
- list_add(&iter->walker.list, &tbl->walkers);
- else
+ if (rcu_head_after_call_rcu(&tbl->rcu, bucket_table_free_rcu))
+ /* This bucket table is being freed, don't re-link it. */
iter->walker.tbl = NULL;
+ else
+ list_add(&iter->walker.list, &tbl->walkers);
spin_unlock(&ht->lock);
out:
@@ -1046,11 +1038,6 @@ int rhashtable_init(struct rhashtable *ht,
size = rounded_hashtable_size(&ht->p);
- if (params->locks_mul)
- ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
- else
- ht->p.locks_mul = BUCKET_LOCKS_PER_CPU;
-
ht->key_len = ht->p.key_len;
if (!params->hashfn) {
ht->p.hashfn = jhash;
@@ -1152,7 +1139,7 @@ restart:
struct rhash_head *pos, *next;
cond_resched();
- for (pos = rht_dereference(*rht_bucket(tbl, i), ht),
+ for (pos = rht_ptr_exclusive(rht_bucket(tbl, i)),
next = !rht_is_a_nulls(pos) ?
rht_dereference(pos->next, ht) : NULL;
!rht_is_a_nulls(pos);
@@ -1179,11 +1166,10 @@ void rhashtable_destroy(struct rhashtable *ht)
}
EXPORT_SYMBOL_GPL(rhashtable_destroy);
-struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
- unsigned int hash)
+struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
+ unsigned int hash)
{
const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
- static struct rhash_head __rcu *rhnull;
unsigned int index = hash & ((1 << tbl->nest) - 1);
unsigned int size = tbl->size >> tbl->nest;
unsigned int subhash = hash;
@@ -1201,20 +1187,28 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
subhash >>= shift;
}
- if (!ntbl) {
- if (!rhnull)
- INIT_RHT_NULLS_HEAD(rhnull);
- return &rhnull;
- }
+ if (!ntbl)
+ return NULL;
return &ntbl[subhash].bucket;
}
+EXPORT_SYMBOL_GPL(__rht_bucket_nested);
+
+struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
+ unsigned int hash)
+{
+ static struct rhash_lock_head __rcu *rhnull;
+
+ if (!rhnull)
+ INIT_RHT_NULLS_HEAD(rhnull);
+ return __rht_bucket_nested(tbl, hash) ?: &rhnull;
+}
EXPORT_SYMBOL_GPL(rht_bucket_nested);
-struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
- struct bucket_table *tbl,
- unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
+ struct bucket_table *tbl,
+ unsigned int hash)
{
const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
unsigned int index = hash & ((1 << tbl->nest) - 1);
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 3bd2e91bfc29..084fe5a6ac57 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -500,7 +500,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt)
struct rhash_head *pos, *next;
struct test_obj_rhl *p;
- pos = rht_dereference(tbl->buckets[i], ht);
+ pos = rht_ptr_exclusive(tbl->buckets + i);
next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL;
if (!rht_is_a_nulls(pos)) {