aboutsummaryrefslogtreecommitdiff
path: root/fs/udf/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/udf/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/udf/unicode.c')
-rw-r--r--fs/udf/unicode.c402
1 files changed, 402 insertions, 0 deletions
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
new file mode 100644
index 000000000..622569007
--- /dev/null
+++ b/fs/udf/unicode.c
@@ -0,0 +1,402 @@
+/*
+ * unicode.c
+ *
+ * PURPOSE
+ * Routines for converting between UTF-8 and OSTA Compressed Unicode.
+ * Also handles filename mangling
+ *
+ * DESCRIPTION
+ * OSTA Compressed Unicode is explained in the OSTA UDF specification.
+ * http://www.osta.org/
+ * UTF-8 is explained in the IETF RFC XXXX.
+ * ftp://ftp.internic.net/rfc/rfcxxxx.txt
+ *
+ * COPYRIGHT
+ * This file is distributed under the terms of the GNU General Public
+ * License (GPL). Copies of the GPL can be obtained from:
+ * ftp://prep.ai.mit.edu/pub/gnu/GPL
+ * Each contributing author retains all rights to their own work.
+ */
+
+#include "udfdecl.h"
+
+#include <linux/kernel.h>
+#include <linux/string.h> /* for memset */
+#include <linux/nls.h>
+#include <linux/crc-itu-t.h>
+#include <linux/slab.h>
+
+#include "udf_sb.h"
+
+#define PLANE_SIZE 0x10000
+#define UNICODE_MAX 0x10ffff
+#define SURROGATE_MASK 0xfffff800
+#define SURROGATE_PAIR 0x0000d800
+#define SURROGATE_LOW 0x00000400
+#define SURROGATE_CHAR_BITS 10
+#define SURROGATE_CHAR_MASK ((1 << SURROGATE_CHAR_BITS) - 1)
+
+#define ILLEGAL_CHAR_MARK '_'
+#define EXT_MARK '.'
+#define CRC_MARK '#'
+#define EXT_SIZE 5
+/* Number of chars we need to store generated CRC to make filename unique */
+#define CRC_LEN 5
+
+static unicode_t get_utf16_char(const uint8_t *str_i, int str_i_max_len,
+ int str_i_idx, int u_ch, unicode_t *ret)
+{
+ unicode_t c;
+ int start_idx = str_i_idx;
+
+ /* Expand OSTA compressed Unicode to Unicode */
+ c = str_i[str_i_idx++];
+ if (u_ch > 1)
+ c = (c << 8) | str_i[str_i_idx++];
+ if ((c & SURROGATE_MASK) == SURROGATE_PAIR) {
+ unicode_t next;
+
+ /* Trailing surrogate char */
+ if (str_i_idx >= str_i_max_len) {
+ c = UNICODE_MAX + 1;
+ goto out;
+ }
+
+ /* Low surrogate must follow the high one... */
+ if (c & SURROGATE_LOW) {
+ c = UNICODE_MAX + 1;
+ goto out;
+ }
+
+ WARN_ON_ONCE(u_ch != 2);
+ next = str_i[str_i_idx++] << 8;
+ next |= str_i[str_i_idx++];
+ if ((next & SURROGATE_MASK) != SURROGATE_PAIR ||
+ !(next & SURROGATE_LOW)) {
+ c = UNICODE_MAX + 1;
+ goto out;
+ }
+
+ c = PLANE_SIZE +
+ ((c & SURROGATE_CHAR_MASK) << SURROGATE_CHAR_BITS) +
+ (next & SURROGATE_CHAR_MASK);
+ }
+out:
+ *ret = c;
+ return str_i_idx - start_idx;
+}
+
+
+static int udf_name_conv_char(uint8_t *str_o, int str_o_max_len,
+ int *str_o_idx,
+ const uint8_t *str_i, int str_i_max_len,
+ int *str_i_idx,
+ int u_ch, int *needsCRC,
+ int (*conv_f)(wchar_t, unsigned char *, int),
+ int translate)
+{
+ unicode_t c;
+ int illChar = 0;
+ int len, gotch = 0;
+
+ while (!gotch && *str_i_idx < str_i_max_len) {
+ if (*str_o_idx >= str_o_max_len) {
+ *needsCRC = 1;
+ return gotch;
+ }
+
+ len = get_utf16_char(str_i, str_i_max_len, *str_i_idx, u_ch,
+ &c);
+ /* These chars cannot be converted. Replace them. */
+ if (c == 0 || c > UNICODE_MAX || (conv_f && c > MAX_WCHAR_T) ||
+ (translate && c == '/')) {
+ illChar = 1;
+ if (!translate)
+ gotch = 1;
+ } else if (illChar)
+ break;
+ else
+ gotch = 1;
+ *str_i_idx += len;
+ }
+ if (illChar) {
+ *needsCRC = 1;
+ c = ILLEGAL_CHAR_MARK;
+ gotch = 1;
+ }
+ if (gotch) {
+ if (conv_f) {
+ len = conv_f(c, &str_o[*str_o_idx],
+ str_o_max_len - *str_o_idx);
+ } else {
+ len = utf32_to_utf8(c, &str_o[*str_o_idx],
+ str_o_max_len - *str_o_idx);
+ if (len < 0)
+ len = -ENAMETOOLONG;
+ }
+ /* Valid character? */
+ if (len >= 0)
+ *str_o_idx += len;
+ else if (len == -ENAMETOOLONG) {
+ *needsCRC = 1;
+ gotch = 0;
+ } else {
+ str_o[(*str_o_idx)++] = ILLEGAL_CHAR_MARK;
+ *needsCRC = 1;
+ }
+ }
+ return gotch;
+}
+
+static int udf_name_from_CS0(struct super_block *sb,
+ uint8_t *str_o, int str_max_len,
+ const uint8_t *ocu, int ocu_len,
+ int translate)
+{
+ uint32_t c;
+ uint8_t cmp_id;
+ int idx, len;
+ int u_ch;
+ int needsCRC = 0;
+ int ext_i_len, ext_max_len;
+ int str_o_len = 0; /* Length of resulting output */
+ int ext_o_len = 0; /* Extension output length */
+ int ext_crc_len = 0; /* Extension output length if used with CRC */
+ int i_ext = -1; /* Extension position in input buffer */
+ int o_crc = 0; /* Rightmost possible output pos for CRC+ext */
+ unsigned short valueCRC;
+ uint8_t ext[EXT_SIZE * NLS_MAX_CHARSET_SIZE + 1];
+ uint8_t crc[CRC_LEN];
+ int (*conv_f)(wchar_t, unsigned char *, int);
+
+ if (str_max_len <= 0)
+ return 0;
+
+ if (ocu_len == 0) {
+ memset(str_o, 0, str_max_len);
+ return 0;
+ }
+
+ if (UDF_SB(sb)->s_nls_map)
+ conv_f = UDF_SB(sb)->s_nls_map->uni2char;
+ else
+ conv_f = NULL;
+
+ cmp_id = ocu[0];
+ if (cmp_id != 8 && cmp_id != 16) {
+ memset(str_o, 0, str_max_len);
+ pr_err("unknown compression code (%u)\n", cmp_id);
+ return -EINVAL;
+ }
+ u_ch = cmp_id >> 3;
+
+ ocu++;
+ ocu_len--;
+
+ if (ocu_len % u_ch) {
+ pr_err("incorrect filename length (%d)\n", ocu_len + 1);
+ return -EINVAL;
+ }
+
+ if (translate) {
+ /* Look for extension */
+ for (idx = ocu_len - u_ch, ext_i_len = 0;
+ (idx >= 0) && (ext_i_len < EXT_SIZE);
+ idx -= u_ch, ext_i_len++) {
+ c = ocu[idx];
+ if (u_ch > 1)
+ c = (c << 8) | ocu[idx + 1];
+
+ if (c == EXT_MARK) {
+ if (ext_i_len)
+ i_ext = idx;
+ break;
+ }
+ }
+ if (i_ext >= 0) {
+ /* Convert extension */
+ ext_max_len = min_t(int, sizeof(ext), str_max_len);
+ ext[ext_o_len++] = EXT_MARK;
+ idx = i_ext + u_ch;
+ while (udf_name_conv_char(ext, ext_max_len, &ext_o_len,
+ ocu, ocu_len, &idx,
+ u_ch, &needsCRC,
+ conv_f, translate)) {
+ if ((ext_o_len + CRC_LEN) < str_max_len)
+ ext_crc_len = ext_o_len;
+ }
+ }
+ }
+
+ idx = 0;
+ while (1) {
+ if (translate && (idx == i_ext)) {
+ if (str_o_len > (str_max_len - ext_o_len))
+ needsCRC = 1;
+ break;
+ }
+
+ if (!udf_name_conv_char(str_o, str_max_len, &str_o_len,
+ ocu, ocu_len, &idx,
+ u_ch, &needsCRC, conv_f, translate))
+ break;
+
+ if (translate &&
+ (str_o_len <= (str_max_len - ext_o_len - CRC_LEN)))
+ o_crc = str_o_len;
+ }
+
+ if (translate) {
+ if (str_o_len <= 2 && str_o[0] == '.' &&
+ (str_o_len == 1 || str_o[1] == '.'))
+ needsCRC = 1;
+ if (needsCRC) {
+ str_o_len = o_crc;
+ valueCRC = crc_itu_t(0, ocu, ocu_len);
+ crc[0] = CRC_MARK;
+ crc[1] = hex_asc_upper_hi(valueCRC >> 8);
+ crc[2] = hex_asc_upper_lo(valueCRC >> 8);
+ crc[3] = hex_asc_upper_hi(valueCRC);
+ crc[4] = hex_asc_upper_lo(valueCRC);
+ len = min_t(int, CRC_LEN, str_max_len - str_o_len);
+ memcpy(&str_o[str_o_len], crc, len);
+ str_o_len += len;
+ ext_o_len = ext_crc_len;
+ }
+ if (ext_o_len > 0) {
+ memcpy(&str_o[str_o_len], ext, ext_o_len);
+ str_o_len += ext_o_len;
+ }
+ }
+
+ return str_o_len;
+}
+
+static int udf_name_to_CS0(struct super_block *sb,
+ uint8_t *ocu, int ocu_max_len,
+ const uint8_t *str_i, int str_len)
+{
+ int i, len;
+ unsigned int max_val;
+ int u_len, u_ch;
+ unicode_t uni_char;
+ int (*conv_f)(const unsigned char *, int, wchar_t *);
+
+ if (ocu_max_len <= 0)
+ return 0;
+
+ if (UDF_SB(sb)->s_nls_map)
+ conv_f = UDF_SB(sb)->s_nls_map->char2uni;
+ else
+ conv_f = NULL;
+
+ memset(ocu, 0, ocu_max_len);
+ ocu[0] = 8;
+ max_val = 0xff;
+ u_ch = 1;
+
+try_again:
+ u_len = 1;
+ for (i = 0; i < str_len; i += len) {
+ /* Name didn't fit? */
+ if (u_len + u_ch > ocu_max_len)
+ return 0;
+ if (conv_f) {
+ wchar_t wchar;
+
+ len = conv_f(&str_i[i], str_len - i, &wchar);
+ if (len > 0)
+ uni_char = wchar;
+ } else {
+ len = utf8_to_utf32(&str_i[i], str_len - i,
+ &uni_char);
+ }
+ /* Invalid character, deal with it */
+ if (len <= 0 || uni_char > UNICODE_MAX) {
+ len = 1;
+ uni_char = '?';
+ }
+
+ if (uni_char > max_val) {
+ unicode_t c;
+
+ if (max_val == 0xff) {
+ max_val = 0xffff;
+ ocu[0] = 0x10;
+ u_ch = 2;
+ goto try_again;
+ }
+ /*
+ * Use UTF-16 encoding for chars outside we
+ * cannot encode directly.
+ */
+ if (u_len + 2 * u_ch > ocu_max_len)
+ return 0;
+
+ uni_char -= PLANE_SIZE;
+ c = SURROGATE_PAIR |
+ ((uni_char >> SURROGATE_CHAR_BITS) &
+ SURROGATE_CHAR_MASK);
+ ocu[u_len++] = (uint8_t)(c >> 8);
+ ocu[u_len++] = (uint8_t)(c & 0xff);
+ uni_char = SURROGATE_PAIR | SURROGATE_LOW |
+ (uni_char & SURROGATE_CHAR_MASK);
+ }
+
+ if (max_val == 0xffff)
+ ocu[u_len++] = (uint8_t)(uni_char >> 8);
+ ocu[u_len++] = (uint8_t)(uni_char & 0xff);
+ }
+
+ return u_len;
+}
+
+/*
+ * Convert CS0 dstring to output charset. Warning: This function may truncate
+ * input string if it is too long as it is used for informational strings only
+ * and it is better to truncate the string than to refuse mounting a media.
+ */
+int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len,
+ const uint8_t *ocu_i, int i_len)
+{
+ int s_len = 0;
+
+ if (i_len > 0) {
+ s_len = ocu_i[i_len - 1];
+ if (s_len >= i_len) {
+ pr_warn("incorrect dstring lengths (%d/%d),"
+ " truncating\n", s_len, i_len);
+ s_len = i_len - 1;
+ /* 2-byte encoding? Need to round properly... */
+ if (ocu_i[0] == 16)
+ s_len -= (s_len - 1) & 2;
+ }
+ }
+
+ return udf_name_from_CS0(sb, utf_o, o_len, ocu_i, s_len, 0);
+}
+
+int udf_get_filename(struct super_block *sb, const uint8_t *sname, int slen,
+ uint8_t *dname, int dlen)
+{
+ int ret;
+
+ if (!slen)
+ return -EIO;
+
+ if (dlen <= 0)
+ return 0;
+
+ ret = udf_name_from_CS0(sb, dname, dlen, sname, slen, 1);
+ /* Zero length filename isn't valid... */
+ if (ret == 0)
+ ret = -EINVAL;
+ return ret;
+}
+
+int udf_put_filename(struct super_block *sb, const uint8_t *sname, int slen,
+ uint8_t *dname, int dlen)
+{
+ return udf_name_to_CS0(sb, dname, dlen, sname, slen);
+}
+