aboutsummaryrefslogtreecommitdiff
path: root/fs/ksmbd/unicode.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /fs/ksmbd/unicode.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'fs/ksmbd/unicode.c')
-rw-r--r--fs/ksmbd/unicode.c384
1 files changed, 384 insertions, 0 deletions
diff --git a/fs/ksmbd/unicode.c b/fs/ksmbd/unicode.c
new file mode 100644
index 000000000..a0db699dd
--- /dev/null
+++ b/fs/ksmbd/unicode.c
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Some of the source code in this file came from fs/cifs/cifs_unicode.c
+ *
+ * Copyright (c) International Business Machines Corp., 2000,2009
+ * Modified by Steve French (sfrench@us.ibm.com)
+ * Modified by Namjae Jeon (linkinjeon@kernel.org)
+ */
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <asm/unaligned.h>
+#include "glob.h"
+#include "unicode.h"
+#include "uniupr.h"
+#include "smb_common.h"
+
+/*
+ * smb_utf16_bytes() - how long will a string be after conversion?
+ * @from: pointer to input string
+ * @maxbytes: don't go past this many bytes of input string
+ * @codepage: destination codepage
+ *
+ * Walk a utf16le string and return the number of bytes that the string will
+ * be after being converted to the given charset, not including any null
+ * termination required. Don't walk past maxbytes in the source buffer.
+ *
+ * Return: string length after conversion
+ */
+static int smb_utf16_bytes(const __le16 *from, int maxbytes,
+ const struct nls_table *codepage)
+{
+ int i;
+ int charlen, outlen = 0;
+ int maxwords = maxbytes / 2;
+ char tmp[NLS_MAX_CHARSET_SIZE];
+ __u16 ftmp;
+
+ for (i = 0; i < maxwords; i++) {
+ ftmp = get_unaligned_le16(&from[i]);
+ if (ftmp == 0)
+ break;
+
+ charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE);
+ if (charlen > 0)
+ outlen += charlen;
+ else
+ outlen++;
+ }
+
+ return outlen;
+}
+
+/*
+ * cifs_mapchar() - convert a host-endian char to proper char in codepage
+ * @target: where converted character should be copied
+ * @src_char: 2 byte host-endian source character
+ * @cp: codepage to which character should be converted
+ * @mapchar: should character be mapped according to mapchars mount option?
+ *
+ * This function handles the conversion of a single character. It is the
+ * responsibility of the caller to ensure that the target buffer is large
+ * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
+ *
+ * Return: string length after conversion
+ */
+static int
+cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
+ bool mapchar)
+{
+ int len = 1;
+
+ if (!mapchar)
+ goto cp_convert;
+
+ /*
+ * BB: Cannot handle remapping UNI_SLASH until all the calls to
+ * build_path_from_dentry are modified, as they use slash as
+ * separator.
+ */
+ switch (src_char) {
+ case UNI_COLON:
+ *target = ':';
+ break;
+ case UNI_ASTERISK:
+ *target = '*';
+ break;
+ case UNI_QUESTION:
+ *target = '?';
+ break;
+ case UNI_PIPE:
+ *target = '|';
+ break;
+ case UNI_GRTRTHAN:
+ *target = '>';
+ break;
+ case UNI_LESSTHAN:
+ *target = '<';
+ break;
+ default:
+ goto cp_convert;
+ }
+
+out:
+ return len;
+
+cp_convert:
+ len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);
+ if (len <= 0) {
+ *target = '?';
+ len = 1;
+ }
+
+ goto out;
+}
+
+/*
+ * is_char_allowed() - check for valid character
+ * @ch: input character to be checked
+ *
+ * Return: 1 if char is allowed, otherwise 0
+ */
+static inline int is_char_allowed(char *ch)
+{
+ /* check for control chars, wildcards etc. */
+ if (!(*ch & 0x80) &&
+ (*ch <= 0x1f ||
+ *ch == '?' || *ch == '"' || *ch == '<' ||
+ *ch == '>' || *ch == '|'))
+ return 0;
+
+ return 1;
+}
+
+/*
+ * smb_from_utf16() - convert utf16le string to local charset
+ * @to: destination buffer
+ * @from: source buffer
+ * @tolen: destination buffer size (in bytes)
+ * @fromlen: source buffer size (in bytes)
+ * @codepage: codepage to which characters should be converted
+ * @mapchar: should characters be remapped according to the mapchars option?
+ *
+ * Convert a little-endian utf16le string (as sent by the server) to a string
+ * in the provided codepage. The tolen and fromlen parameters are to ensure
+ * that the code doesn't walk off of the end of the buffer (which is always
+ * a danger if the alignment of the source buffer is off). The destination
+ * string is always properly null terminated and fits in the destination
+ * buffer. Returns the length of the destination string in bytes (including
+ * null terminator).
+ *
+ * Note that some windows versions actually send multiword UTF-16 characters
+ * instead of straight UTF16-2. The linux nls routines however aren't able to
+ * deal with those characters properly. In the event that we get some of
+ * those characters, they won't be translated properly.
+ *
+ * Return: string length after conversion
+ */
+static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
+ const struct nls_table *codepage, bool mapchar)
+{
+ int i, charlen, safelen;
+ int outlen = 0;
+ int nullsize = nls_nullsize(codepage);
+ int fromwords = fromlen / 2;
+ char tmp[NLS_MAX_CHARSET_SIZE];
+ __u16 ftmp;
+
+ /*
+ * because the chars can be of varying widths, we need to take care
+ * not to overflow the destination buffer when we get close to the
+ * end of it. Until we get to this offset, we don't need to check
+ * for overflow however.
+ */
+ safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);
+
+ for (i = 0; i < fromwords; i++) {
+ ftmp = get_unaligned_le16(&from[i]);
+ if (ftmp == 0)
+ break;
+
+ /*
+ * check to see if converting this character might make the
+ * conversion bleed into the null terminator
+ */
+ if (outlen >= safelen) {
+ charlen = cifs_mapchar(tmp, ftmp, codepage, mapchar);
+ if ((outlen + charlen) > (tolen - nullsize))
+ break;
+ }
+
+ /* put converted char into 'to' buffer */
+ charlen = cifs_mapchar(&to[outlen], ftmp, codepage, mapchar);
+ outlen += charlen;
+ }
+
+ /* properly null-terminate string */
+ for (i = 0; i < nullsize; i++)
+ to[outlen++] = 0;
+
+ return outlen;
+}
+
+/*
+ * smb_strtoUTF16() - Convert character string to unicode string
+ * @to: destination buffer
+ * @from: source buffer
+ * @len: destination buffer size (in bytes)
+ * @codepage: codepage to which characters should be converted
+ *
+ * Return: string length after conversion
+ */
+int smb_strtoUTF16(__le16 *to, const char *from, int len,
+ const struct nls_table *codepage)
+{
+ int charlen;
+ int i;
+ wchar_t wchar_to; /* needed to quiet sparse */
+
+ /* special case for utf8 to handle no plane0 chars */
+ if (!strcmp(codepage->charset, "utf8")) {
+ /*
+ * convert utf8 -> utf16, we assume we have enough space
+ * as caller should have assumed conversion does not overflow
+ * in destination len is length in wchar_t units (16bits)
+ */
+ i = utf8s_to_utf16s(from, len, UTF16_LITTLE_ENDIAN,
+ (wchar_t *)to, len);
+
+ /* if success terminate and exit */
+ if (i >= 0)
+ goto success;
+ /*
+ * if fails fall back to UCS encoding as this
+ * function should not return negative values
+ * currently can fail only if source contains
+ * invalid encoded characters
+ */
+ }
+
+ for (i = 0; len > 0 && *from; i++, from += charlen, len -= charlen) {
+ charlen = codepage->char2uni(from, len, &wchar_to);
+ if (charlen < 1) {
+ /* A question mark */
+ wchar_to = 0x003f;
+ charlen = 1;
+ }
+ put_unaligned_le16(wchar_to, &to[i]);
+ }
+
+success:
+ put_unaligned_le16(0, &to[i]);
+ return i;
+}
+
+/*
+ * smb_strndup_from_utf16() - copy a string from wire format to the local
+ * codepage
+ * @src: source string
+ * @maxlen: don't walk past this many bytes in the source string
+ * @is_unicode: is this a unicode string?
+ * @codepage: destination codepage
+ *
+ * Take a string given by the server, convert it to the local codepage and
+ * put it in a new buffer. Returns a pointer to the new string or NULL on
+ * error.
+ *
+ * Return: destination string buffer or error ptr
+ */
+char *smb_strndup_from_utf16(const char *src, const int maxlen,
+ const bool is_unicode,
+ const struct nls_table *codepage)
+{
+ int len, ret;
+ char *dst;
+
+ if (is_unicode) {
+ len = smb_utf16_bytes((__le16 *)src, maxlen, codepage);
+ len += nls_nullsize(codepage);
+ dst = kmalloc(len, GFP_KERNEL);
+ if (!dst)
+ return ERR_PTR(-ENOMEM);
+ ret = smb_from_utf16(dst, (__le16 *)src, len, maxlen, codepage,
+ false);
+ if (ret < 0) {
+ kfree(dst);
+ return ERR_PTR(-EINVAL);
+ }
+ } else {
+ len = strnlen(src, maxlen);
+ len++;
+ dst = kmalloc(len, GFP_KERNEL);
+ if (!dst)
+ return ERR_PTR(-ENOMEM);
+ strscpy(dst, src, len);
+ }
+
+ return dst;
+}
+
+/*
+ * Convert 16 bit Unicode pathname to wire format from string in current code
+ * page. Conversion may involve remapping up the six characters that are
+ * only legal in POSIX-like OS (if they are present in the string). Path
+ * names are little endian 16 bit Unicode on the wire
+ */
+/*
+ * smbConvertToUTF16() - convert string from local charset to utf16
+ * @target: destination buffer
+ * @source: source buffer
+ * @srclen: source buffer size (in bytes)
+ * @cp: codepage to which characters should be converted
+ * @mapchar: should characters be remapped according to the mapchars option?
+ *
+ * Convert 16 bit Unicode pathname to wire format from string in current code
+ * page. Conversion may involve remapping up the six characters that are
+ * only legal in POSIX-like OS (if they are present in the string). Path
+ * names are little endian 16 bit Unicode on the wire
+ *
+ * Return: char length after conversion
+ */
+int smbConvertToUTF16(__le16 *target, const char *source, int srclen,
+ const struct nls_table *cp, int mapchars)
+{
+ int i, j, charlen;
+ char src_char;
+ __le16 dst_char;
+ wchar_t tmp;
+
+ if (!mapchars)
+ return smb_strtoUTF16(target, source, srclen, cp);
+
+ for (i = 0, j = 0; i < srclen; j++) {
+ src_char = source[i];
+ charlen = 1;
+ switch (src_char) {
+ case 0:
+ put_unaligned(0, &target[j]);
+ return j;
+ case ':':
+ dst_char = cpu_to_le16(UNI_COLON);
+ break;
+ case '*':
+ dst_char = cpu_to_le16(UNI_ASTERISK);
+ break;
+ case '?':
+ dst_char = cpu_to_le16(UNI_QUESTION);
+ break;
+ case '<':
+ dst_char = cpu_to_le16(UNI_LESSTHAN);
+ break;
+ case '>':
+ dst_char = cpu_to_le16(UNI_GRTRTHAN);
+ break;
+ case '|':
+ dst_char = cpu_to_le16(UNI_PIPE);
+ break;
+ /*
+ * FIXME: We can not handle remapping backslash (UNI_SLASH)
+ * until all the calls to build_path_from_dentry are modified,
+ * as they use backslash as separator.
+ */
+ default:
+ charlen = cp->char2uni(source + i, srclen - i, &tmp);
+ dst_char = cpu_to_le16(tmp);
+
+ /*
+ * if no match, use question mark, which at least in
+ * some cases serves as wild card
+ */
+ if (charlen < 1) {
+ dst_char = cpu_to_le16(0x003f);
+ charlen = 1;
+ }
+ }
+ /*
+ * character may take more than one byte in the source string,
+ * but will take exactly two bytes in the target string
+ */
+ i += charlen;
+ put_unaligned(dst_char, &target[j]);
+ }
+
+ return j;
+}