mirror of
https://github.com/MHSanaei/3x-ui.git
synced 2026-07-17 18:16:08 +00:00
5e1cb7693b
* fix(email): resolve a name-addr smtpFrom into bare envelope address and display name The save-time validator accepts any RFC 5322 address form, so a value like '3x-ui Panel <panel(at)example.com>' passes validation, but Send and TestConnection fed that raw string to MAIL FROM, which strict servers reject with 501, and buildMessage mangled it into a quoted local part. Parse the configured sender at the point of use: the envelope gets the bare address and, when no explicit sender name is set, the display name embedded in the setting is used for the From header. * fix(email): report a missing sender address from the SMTP connection test TestConnection skipped the empty-from guard that Send enforces, so with no sender and no username configured the test issued the null reverse-path and could report success against a lenient relay while every real notification send kept failing with the missing-sender error. Guard the test path the same way and surface a dedicated translated message. * fix(sub): fall back to the raw subscription when an auto-detected format has no content With format auto-detection enabled, a client whose User-Agent matched the Clash or JSON regex was routed straight to that format handler. For a subscription whose entries convert to neither format (an MTProto-only subscription, for example) the handler returns an empty document and the request ended as 404, breaking a URL that served the raw list before the toggle. The auto-detect branches now serve the detected format only when it produces content and otherwise continue to the raw response; the explicit format endpoints keep answering 404 for empty documents. * fix(node): match prefixed central tags when filtering a selected-mode node snapshot FilterNodeSnapshot compared a node snapshot's inbound tags against the raw selected-tag list with an exact match, while its two siblings (SnapshotHasUnadoptedInbounds and the reconcile tagToCentral map) expand each selected tag to both its bare node-side form and its n<id>- prefixed central form. A panel-created node inbound is recorded in the selected list under the central prefixed tag but reported by the node under the bare tag, so the exact match dropped it from every snapshot and the orphan sweep then deleted its central row one tick after creation. Expand the allowed set with the same prefix flip the siblings use. * fix(client): refuse a bulk quota reduction that would fall to or below zero BulkAdjust clamped a client's new traffic limit with max(total+addBytes, 0). Because 0 is the unlimited sentinel, reducing a client's quota by more than it had left silently granted that client unlimited traffic. The sibling expiry branch already refuses an over-reduction; mirror it for quota so the adjustment is skipped with a clear reason instead of crossing the sentinel. * fix(client): persist a bulk adjustment's applied field even when the sibling field is skipped In a mixed BulkAdjust (both a days delta and a bytes delta), a per-field planning skip such as "unlimited expiry" or "unlimited traffic" was recorded in the same map that gated the client_traffics write. The applied field was already written to the inbound JSON and the clients table, but the enforcement row was left untouched, so the depletion job cut the client on the old limit while the panel showed the new one. Gate the traffic-row write on an actual inbound-processing failure rather than on any planning-phase skip note. * fix(inbound): always create in AddInbound instead of overwriting a row whose id was posted The add controller binds the inbound model's id form field and never clears it, and AddInbound persisted with GORM Save, which updates in place when the primary key is non-zero. A client that reused an existing id (for instance by duplicating an inbound fetched from /get and changing the port) silently overwrote that stored row instead of creating a new inbound. Zero the id at the top of AddInbound, matching how it already zeroes the client-stat ids. * fix(inbound): accept WireGuard clients when creating an inbound AddInbound's per-client validation switch had cases for every protocol except WireGuard, so a WireGuard client fell through to the default branch that requires a non-empty id. WireGuard clients are keyed by their public key and carry no id, so importing a WireGuard inbound or re-adding one to a reconciling node was rejected with "empty client ID". Add a wireguard case that validates the client key, mirroring addInboundClient. * fix(client): stop holding the inbound-lock registry mutex while waiting on one inbound lockInbound acquired the global registry mutex and then blocked on the per-inbound mutex without releasing the registry first. A slow client operation holding one inbound's mutex (for example a bulk delete pushing to an unreachable node) made the next waiter park on that inbound while still holding the registry mutex, which in turn blocked lockInbound for every other inbound — freezing client mutations panel-wide. Release the registry mutex before taking the per-inbound lock. * fix(client): honor keepTraffic when deleting a client that is attached to inbounds Delete, DeleteByEmail and BulkDelete all pass keepTraffic to their final cleanup transaction, but each called the per-inbound delete helper with a hardcoded false. That helper purges the client's traffic, IP and stat rows before the gated cleanup runs, so keepTraffic=true still destroyed all traffic history for any client actually attached to an inbound (the pinned test only covered a record with no inbound mappings). Thread the caller's keepTraffic through to the per-inbound helper at all three call sites. * fix(inbound): defer a local MTProto inbound edit's sidecar push until after commit UpdateInbound applied a local MTProto inbound change by calling the runtime UpdateInbound (which stops/starts the mtg sidecar or talks to it) from inside runSerializedTx. That runs process and network I/O on the single traffic-writer goroutine while a DB transaction is open, so a slow sidecar stalls traffic accounting and every concurrent client mutation, and a later step failing the transaction leaves the sidecar ahead of the rolled-back row. Move the push into the post-commit hook, matching the xray branch. Adds a SetLocalRuntimeOverride test seam mirroring the existing node override so the deferral is regression tested. * fix(client): delete external-link rows when bulk-deleting clients The single-client Delete path removes a client's client_external_links rows, but BulkDelete (and the DelDepleted reaper that routes through it) deleted the record, mappings and traffic while leaving the external-link rows keyed by the now-dead client id, so they accumulated as orphans. Delete them in the same cleanup transaction, keyed by client id like the single path. * fix(inbound): request an xray restart when toggling a routed MTProto inbound AddInbound, DelInbound and UpdateInbound all flag needRestart when an inbound routes MTProto through xray, so the egress SOCKS bridge is regenerated. Only SetInboundEnable's local path omitted it, so toggling a routed MTProto inbound off then on left the bridge out of the running config while the sidecar dialed its loopback port, blackholing that inbound until an unrelated restart. Flag the restart on the local enable path too. * fix(client): apply enable-by-email to every inbound a client is attached to ToggleClientEnableByEmail (Telegram bot) and SetClientEnableByEmail (LDAP sync) resolved a single inbound via the legacy client_traffics pointer and flipped enable only there. A client attached to several inbounds kept connecting through the siblings' running Xray after being disabled, and the next edit could re-enable it everywhere from a stale sibling. Route both through the applyClientFieldByEmail fan-out (the #5039 fix path) so the whole multi-inbound identity is toggled at once, dropping the circular Set/Toggle dependency. * fix(traffic): commit a traffic tick even when a best-effort maintenance helper fails addTrafficLocked stages the inbound and client deltas, then runs three helpers (auto-renew, disable depleted clients, disable depleted inbounds) that are meant to log and continue. All three reused the function-scope err that the deferred commit/rollback inspects, so the last helper's error decided the whole tick: a failure in disableInvalidInbounds rolled back the already-staged traffic while AddTraffic reported success, and because xray had already advanced its counter baseline that traffic was lost for good. Give each best-effort helper its own error variable so only a genuine staging failure rolls the tick back. * fix(traffic): re-enable clients and serialize the write in Reset All Client Traffic ClientService.ResetAllTraffics zeroed up/down but, unlike every sibling reset path, never restored enable=true, so clients that had been auto-disabled for exceeding their quota stayed cut with zero usage after a reset. It also wrote client_traffics directly on the shared DB handle instead of through the serial traffic writer, reintroducing the cross-transaction lock-order deadlock the writer exists to prevent. Restore enable and run the reset inside submitTrafficWrite within one transaction. * fix(traffic): keep node reset propagation out of the serial traffic writer ResetAllTraffics and ResetInboundTraffic performed their remote-node reset HTTP calls inside submitTrafficWrite. Each call can block up to the remote timeout, and Reset All Traffics loops every node serially, so the single traffic-writer goroutine was held for seconds — long enough that the concurrent 5s traffic poll timed out submitting its own write and dropped the deltas it had already drained from xray. Do the DB reset inside the writer, then propagate to the nodes after it returns, matching how the mtproto quota reset is already sequenced. * fix(sub): stop the subscription from 500ing on valid-but-unusual stream settings The raw share-link generators used unchecked type assertions and unguarded array indexing: an empty Reality shortIds/serverNames array (random.Num(0) panics), a tcp-http header with no request block or an empty request.path, a grpc block missing its keys, empty stream settings, and a non-string Host header all panicked mid-generation. Because getSubs loops every client's link with no recover, one such client 500s the entire subscription for everyone. The sibling JSON, Clash and frontend generators already guard these; make the raw generators match with comma-ok assertions and length checks. * fix(sub): tolerate a hysteria inbound without hysteriaSettings in the JSON subscription genHy asserted stream["hysteriaSettings"].(map[string]any) without the comma-ok form, so a hysteria inbound whose StreamSettings omit the hysteriaSettings key (a valid, representable shape the raw generator renders fine) panicked and 500ed the entire JSON subscription. Use comma-ok; the downstream reads already guard each key, so a nil map degrades gracefully. * fix(sub): emit the pinned peer cert sha256 in Clash subscriptions The Clash stream builder computed tlsSettings["pin-sha256"] from the inbound's pinnedPeerCertSha256, but applySecurity's tls case never copied it onto the proxy, so it was written with no reader and silently dropped. Clash subscribers lost certificate pinning while JSON subscribers kept it. Surface pin-sha256 on the proxy in the tls case, matching the JSON emitter. * fix(link): parse the snake_case and extra-blob xhttp fields when importing a share link The panel's share-link emitters (Go and TS) carry advanced xhttp knobs as a snake_case x_padding_bytes plus an extra=<json> payload, but the Go parser's xhttp branch read only top-level camelCase params, so importing an xhttp link via the outbound-subscription feature dropped xPaddingBytes, scMaxEachPostBytes and the rest, silently reverting them to the stream defaults and producing a non-working outbound. Mirror the TS parser: read the snake_case alias, merge the extra JSON blob, then let explicit camelCase params win. * fix(frontend): decode URL-safe base64 when parsing an imported share link Base64.decode called window.atob directly, which rejects the base64url alphabet (- and _) and unpadded input. But the panel's own share-link emitter uses Base64.encode(x, true) (URL-safe, unpadded), and real SIP002 links do too, so importing a Shadowsocks link whose method:password encodes with a - or _ threw, fell back to the raw undecoded string, and produced a wrong method and garbage password (the vmess parser shared the same limitation). Normalize base64url and re-pad before atob so decode round-trips every emitted link. * fix(link): honor the vmess ws path and hysteria2 vcn params on import Two Go/TS parser parity gaps in the outbound share-link import path: parseVmess only applied a ws link's path when the inner JSON also carried a host key, so a generator that omits host dropped the path back to the default; and parseHysteria2 hardcoded verifyPeerCertByName to empty, ignoring the vcn param the panel emits, so a hysteria2 outbound with a decoy SNI and a distinct cert name failed TLS verification after import. The TS parser handles both; make the Go parser match. * fix(ui): stop the sniffing form island from clobbering unrendered fields antd's Form.useWatch only reports registered fields, so while the sniffing toggle was off the island emitted { enabled: false } upward and replaced the full Sniffing object in form state. Saving a VLESS reverse outbound then crashed in sniffingToWire on the missing ipsExcluded array; the loopback outbound and the inbound sniffing tab shared the same hole. Watch the store with preserve: true so unrendered fields keep their values, and seed a missing value from the schema defaults instead of an empty cast. * fix(sub): drop empty remark segments instead of leaving a stray separator expandSegment dropped a "|" segment only when its tokens rendered the unlimited mark, so a segment whose only token resolved to the empty string (a client with no comment, an unlimited client's expiry date) was kept as bare decoration, leaving a trailing "|" or a dangling emoji on every share link's remark. Drop a token-bearing segment whenever none of its tokens produce a real value, while still keeping pure-literal segments. * fix(xray): keep source- and domains-scoped routing rules when an inbound is deleted removeInboundTagFromRules drops a routing rule whose inboundTag list becomes empty only if the rule has no other matcher, but routingMatcherKeys omitted xray-core's canonical source and domains keys. A rule scoped by source or domains (common in hand-authored or imported configs) therefore lost its whole body — including a security-relevant block — when its single listed inbound was deleted, instead of just having the tag trimmed. Recognize source and domains as live matchers. * fix(xray): guard RemoveUser against an uninitialized handler client Every XrayAPI handler method returns an error when HandlerServiceClient is nil, except RemoveUser, which dereferenced it directly. A depletion sweep runs Init with the port ignored and, during a restart window where the fresh process's api port is still 0, Init fails and leaves the client nil — so RemoveUser panicked (recovered by the traffic writer, but re-thrown every poll) instead of returning an error. Add the same nil guard the siblings have. * fix(xray): do not revive a manually stopped Xray on a background restart RestartXray cleared isManuallyStopped unconditionally at its top, so the @30s pending-config cron (and warp/ldap/outbound reconcile jobs) that call RestartXray(false) resurrected an Xray the admin had deliberately stopped — unlike the crash-detector, which honors the manual-stop flag. Skip a non-forced restart while the stop flag is set; only an explicit forced restart clears it. * fix(xray): retry a failed pending-restart instead of dropping the config change The 30s cron consumed the need-restart flag with IsNeedRestartAndSetFalse before calling RestartXray and only logged a failure. If RestartXray failed early (a transient GetXrayConfig DB error) the old process kept running the old config, the crash detector saw a running process and never retried, and the flag stayed cleared — so an admin's saved change silently never reached the core. Move the consume/restart/retry into ApplyPendingRestart, which re-arms the flag on failure so the next tick retries. * fix(xray): synchronize the process version and apiPort fields Start writes p.version and p.apiPort (via refreshVersion/refreshAPIPort) after flipping the process to running, while GetXrayVersion and GetAPIPort read them lock-free from the status and traffic poll goroutines. The struct mutex deliberately excluded these fields, so a restart racing a poll was a real data race — a torn read of the version string header can crash. Extend the mutex to cover version and apiPort, doing the blocking version probe before taking the lock. * fix(settings): detect a wildcard listen collision between the web and sub ports The web/sub same-port check compared the two listen addresses as raw strings, so binding both on all interfaces with different spellings (webListen 0.0.0.0 vs an empty subListen) slipped past validation and only failed at startup with an opaque bind error. Treat any wildcard listen ('', 0.0.0.0, ::) as overlapping so the clash is reported up front, while still allowing two distinct specific addresses to share a port. * fix(db): mark the IP-limit cleanup seeder done on a fresh install ResetIpLimitNoFail2ban is a one-time migration that, on a host without fail2ban, zeroes every existing client's limitIp because the limit can't be enforced. It was missing from the fresh-install fast-path seeder list, so on a brand-new DB it did not run on the first boot but fired on the second — wiping any IP limits the admin had set in between. Add it to the fast-path so a truly fresh install marks it done up front (there is nothing to clean), leaving later admin-set limits intact. * fix(security): dial outbound subscriptions through the SSRF guard The outbound-subscription fetch validated the URL host once (resolving DNS and rejecting private targets) but then fetched with a plain HTTP client that re-resolves the host at dial time, so a subscription domain the attacker controls could pass validation as a public IP and rebind to 127.0.0.1 / a cloud metadata endpoint / an internal host for the actual dial — a blind SSRF into the panel's network. Route the direct fetch (and its redirects) through netsafe.SSRFGuardedDialContext, which resolves, checks and dials the same IP atomically, carrying the subscription's AllowPrivate flag on the request context; a configured egress proxy still dials its loopback bridge unguarded. * fix(security): bound the login-limiter attempts map The login rate limiter keys its records on the caller-supplied username and only evicted a record when that exact key was revisited or the login succeeded. An unauthenticated attacker replaying one CSRF token while rotating a fresh username per request seeded a record that was never revisited, growing the map without bound until the panel OOMs. Cap the map: before inserting a new record, reclaim records whose block has lapsed and whose failures aged out, and if the map is still at the ceiling under a broad flood, drop one so memory can never grow past the cap. * fix(tgbot): require admin for privileged callbacks, not just the first switch answerCallback wraps only its first callback switch in an isAdmin guard; the second switch (server usage, inbound/online enumeration, database backup export, ban logs, mass traffic reset, client creation) ran for every caller. Telegram delivers a callback with the tapping user's id, so a non-admin who can see an admin's inline keyboard — as when the bot runs in a group — could tap Backup and receive the full database and config, or reset all traffic. Default-deny before the second switch: a non-admin may only run the per-user client_* callbacks that resolve their own data from their Telegram id. * fix(eventbus): dispatch each subscriber in its own goroutine The fan-out loop called every subscriber's handler sequentially on the single dispatch goroutine. The email and Telegram notifiers block on network I/O for tens of seconds (or minutes when the remote is slow), so one slow subscriber stalled the whole loop: the 256-slot channel then filled and Publish silently dropped later events — including high-value xray.crash and node.down notifications unrelated to the slow handler. Hand each delivered event to every handler in its own goroutine so a blocking subscriber can no longer stall delivery to the others. safeCall already recovers panics, so a detached handler cannot take down the bus. * fix(integration): cap WARP API response body size doWarpRequest read the response with an unbounded io.ReadAll, unlike the sibling NordVPN client which already caps every read at maxResponseSize. A hostile panel egress proxy or a MITM on the Cloudflare WARP endpoint could stream an arbitrarily large body and force the panel into an unbounded allocation. Wrap the body in an io.LimitReader(maxResponseSize) to match the NordVPN client. * fix(email): bound every SMTP step with a connection deadline The "starttls"/"none" transport delivered through net/smtp.SendMail, which dials with an untimed net.Dial and never sets a socket deadline. When an SMTP server accepted the TCP connection but then stalled (or was a blackhole), the caller was released by Send's 30s select, but the sender goroutine and its socket stayed blocked until the OS TCP timeout — minutes per notification, leaking a goroutine and a connection each time. sendWithTLS dialed with a timeout but likewise armed no deadline on the protocol phase, and TestConnection (called synchronously from the settings handler, with no select guard) could hang the request indefinitely. Replace SendMail with sendPlain, which dials with smtpConnectTimeout and arms conn.SetDeadline(smtpDeadline) before the greeting read, preserving SendMail's opportunistic STARTTLS upgrade. Arm the same deadline in sendWithTLS and TestConnection so every SMTP step is bounded. * fix(server): guard access-log parser against malformed lines GetXrayLogs split each Xray access-log line on whitespace and then read fixed offsets — parts[1] for the timestamp and parts[i+1] after the "from", "accepted" and "email:" markers — without checking the line had that many fields. A truncated or malformed line (the logged destination is attacker-influenced) indexed past the slice and panicked; the panel handler returned a 500 via Gin's recovery. Extract the per-line field parsing into parseAccessLogFields and length guard every positional lookup so a short line yields a partial entry instead of panicking. * fix(server): guard xray key-generator output parsing GetNewX25519Cert, GetNewmldsa65 and GetNewmlkem768 parsed xray's stdout by reading lines[0], lines[1] and each line's second colon-separated field without any length check — unlike GetNewEchCert, which already guards its line count. If the xray binary printed fewer than two lines or reformatted its labels (a version change, or a silent failure that emitted nothing), the fixed slice index panicked and the handler 500'd. Extract the shared parsing into parseXrayKeyPairOutput, which length guards the line count and each label split and returns an error instead of panicking, then route all three generators through it. * fix(tgbot): stop auto-deleted messages from resetting wizard state SendMsgToTgbotDeleteAfter spawns a goroutine that, after the display delay, deleted the transient message and then unconditionally cleared the chat's conversation state. Every caller that ends a wizard step already clears the state synchronously, so that call was redundant — and harmful: if within the delay the user advanced to the next step (a callback sets a fresh awaiting_* state), the late goroutine wiped it, and the user's next message fell through unrecognized, silently dropping their input. Move the delayed deletion into deleteMessageAfterDelay, which only removes the message and no longer touches the conversation state. Guard deleteMessageTgBot against a nil bot so the deletion path is unit-testable. * fix(frontend): refetch a fresh CSRF token on 403 instead of reusing the stale meta tag On a 403 to an unsafe method the client cleared its cached CSRF token and called ensureCsrfToken to retry. But ensureCsrfToken prefers the <meta name="csrf-token"> tag baked into the page, which the production panel always injects, so the "refresh" re-read the same stale token and the /csrf-token refetch was never reached — the retry re-sent the token that had just been rejected and the save failed with an error toast. The token lives in the session and rotates when the session is regenerated (for example re-login in another tab), leaving the tab's baked-in meta token stale. Fetch the current token straight from /csrf-token in the 403 branch so the retry uses the authoritative server value. The existing tests only passed because they strip the meta tag; the new test keeps a stale tag present. * fix(frontend): surface backend error text from failed requests HttpUtil.get/post read the thrown HttpError body as response.data.message, but the backend error envelope (entity.Msg) serializes its text as msg. On any non-2xx JSON response the real reason was therefore dropped and the operator saw only the generic "Request failed with status N" toast. Read response.data.msg first (keeping message and the native error text as fallbacks). The sibling test had pinned the wrong body shape ({ message }); correct it to the real backend shape ({ success:false, msg }) so it exercises the actual envelope. * fix(frontend): share one WebSocket connection across bridge and hooks websocketBridge.ts and useWebSocket.ts each declared their own module-scoped sharedClient plus an identical getSharedClient, so the "shared" client was not shared between them: whenever a page using useWebSocket (Clients/Inbounds) mounted alongside the always-mounted bridge, the panel opened two sockets to /ws. The server then pushed every traffic/stats/nodes/inbounds snapshot to both, doubling WebSocket bandwidth and running two independent reconnect loops, and the hook's socket was never disconnected on unmount. Hoist a single getSharedWebSocketClient into api/websocket.ts and route both the bridge and the hook through it, so exactly one connection is opened. * fix(frontend): guard the outbounds WebSocket handler against non-array payloads onOutbounds wrote the raw WebSocket payload straight into the outboundsTraffic cache, unlike the sibling onNodes/onInbounds handlers which first check Array.isArray. A malformed non-array push (for example an object) would land in the cache with staleTime Infinity; consumers that call .find()/.map() on the outbounds list would then throw and crash the Outbounds tab. Add the same Array.isArray guard so a bad push is ignored. * fix(frontend): key the node table by the computed row key, not id The desktop node table used rowKey="id", but transitive sub-nodes (the read-only rows surfaced from downstream nodes) all carry id 0, so a topology with two or more transitive rows gave React duplicate keys. antd's rowKey prop overrides the row object's own computed `key` (`t-${guid}` for transitive rows, the numeric id otherwise), so the unique key the code already builds was ignored — causing row-state/DOM mis-association on any re-render (heartbeat refetch, address-eye toggle). The mobile card path already keyed by record.key. Key the table by "key" so transitive rows get their distinct t-${guid} identity; direct nodes keep key === id, so row selection (filtered to numeric keys) is unchanged. * fix(frontend): map routing row actions through the rule's real index The routing table hides balancer-loopback rules (`_bl_*`) but keeps each visible row's original index in `key`, then handed antd's positional row index straight to edit/delete/toggle/move/drag — all of which mutate the full, unfiltered routing.rules array. Once a hidden loopback rule precedes a visible one (e.g. a balancer whose fallback is another balancer, plus any rule added afterwards), the positional index no longer matches the array index, so deleting or editing a rule silently hit the wrong one — including destroying the loopback rule that keeps the balancer alive. Add originalRuleIndex to translate a positional row index back through the row's `key`, and route every mutating handler (openEdit, confirmDelete, toggleRule, moveUp/moveDown, drag) through it. When no loopback rows are hidden the mapping is the identity, so ordinary configs are unaffected. * fix(frontend): map outbound row actions through the outbound's real index The outbounds table hides balancer-loopback outbounds (`_bl_*`) but keeps each visible row's original index in `key`, then passed antd's positional row index to edit/delete/move and to the per-row probe (onTest) and its result lookup — all of which address the full, unfiltered outbounds array. Once a hidden loopback outbound precedes a visible one, the positional index diverges from the array index, so deleting or editing an outbound hit the wrong one (its deletion-impact plan and removal targeting the wrong entry), and the test button probed / showed results against the wrong outbound. Add originalOutboundIndex and route the mutating handlers through it; key the probe trigger and test-result columns by record.key. With no loopback rows hidden the mapping is the identity, so ordinary configs are unaffected. * fix(frontend): tolerate a malformed happyEyeballs value in the Xray Basics tab BasicsTab derived directHappyEyeballs by calling HappyEyeballsSchema.parse during render, guarding only against null/non-object. A wrong-typed field (e.g. happyEyeballs.tryDelayMs as a string) or any other shape mismatch — reachable via the Complete Template JSON editor or an imported config — threw straight out of render, white-screening the default Xray landing tab. Use safeParse and fall back to null so a bad value degrades to "no override" instead of crashing the page. * fix(frontend): preserve routing-rule fields the form does not surface The rule form rebuilt the rule from a fixed literal of only the fields it edits, and RoutingTab replaces the rule wholesale on confirm. Fields the form never exposes — localPort, localIP, process, ruleTag, webhook — are in the rule schema and can arrive via the advanced JSON editor or Import Rules; opening such a rule in the form and saving silently dropped them. Carry over every key of the original rule the form does not manage before applying the form-derived fields, so an edit only touches what it surfaces. * fix(frontend): re-sync the sniffing island when its value changes externally The sniffing config editor froze its seed value at mount and only watched its own inner AntD form, never reflecting a later change to the shared RHF `sniffing` path. Because the inbound form mounts every tab with forceRender, the friendly Sniffing tab and the Advanced JSON editor are live at once: editing sniffing in the JSON editor updated the RHF value but not the frozen island, so the next interaction with the friendly tab emitted the stale value and silently discarded the JSON edit. Add an effect that pushes an external value change into the inner form, guarded by the same lastEmitted marker the emit path uses so the island never re-seeds from its own echo and no update loop forms. * fix(frontend): don't drift a client's byte quota on a no-op save The quota field shows the total in GB rounded to two decimals; editing a client and saving converted that display value straight back to bytes. A byte total not aligned to 0.01 GB — one set via the API or an import — was therefore rewritten to the rounded value on any save that never touched the field, losing a few MB each time. Add resolveTotalBytes: keep the original byte total when the displayed GB still matches it, and only re-derive from GB when the user actually changed the field. * fix(eventbus): deliver events on a bounded per-subscriber worker The previous fix dispatched each event to every subscriber with a bare `go safeCall`. That unblocked the dispatch loop, but removed the bus's backpressure: under a login-attempt flood (which both notifier subscribers process without rate-limiting) with email/Telegram enabled, every attempt spawned handler goroutines that each block on network I/O for up to ~30s, with no bound — a goroutine and outbound-connection storm. It also let a subscriber's handler run concurrently with itself, racing the Telegram notifier's lazily-cached hostname. Give each subscriber its own bounded queue drained by a single worker goroutine. Dispatch does a non-blocking send per subscriber (dropping only that subscriber's event when its queue is full), so a slow subscriber still can't stall the others, concurrency is bounded to one in-flight handler per subscriber, per-subscriber event order is preserved, and Stop again waits for in-flight handlers to finish. * fix(frontend): map outbound mobile-card actions through the real index too The desktop outbounds table was keyed by the outbound's real index, but the mobile card list was left keying the probe trigger and every test-state lookup by the positional row index. With a hidden balancer-loopback outbound present, tapping Check on a mobile card probed the wrong outbound and the Test-All results landed on the wrong card. Key onTest and the testResult/isTesting reads by record.key, matching the desktop columns. * fix(frontend): meet WCAG AA contrast on the config-block link text The Storybook accessibility test flagged the share-link <code> block: with no explicit color it inherited a muted grey that renders as #888888 on the #f8f8f8 tertiary-fill background in CI's Chromium — a 3.33:1 contrast, below the 4.5:1 AA threshold. Set the text to the theme's primary text token so the colour is explicit and high-contrast in both light and dark themes instead of depending on an inherited value that varies by browser. * style(sub): simplify a negated conjunction to satisfy staticcheck QF1001 golangci-lint (staticcheck QF1001) flagged the `!(a && b)` guard in expandSegment. Rewrite it via De Morgan's law to the equivalent `!a || !b` form so the linter passes; behavior is unchanged. * fix: close panics and races the audit's own fixes left nearby Second-pass review of the 54-commit self-correcting audit. Each item below was confirmed by reading the surrounding source (and, where practical, the pre-fix code) before being changed; regression tests are included for every behavioral fix. Concurrency: - eventbus: Bus.Subscribe called wg.Add with no synchronization against a concurrent Bus.Stop's wg.Wait, a real "WaitGroup misuse" panic risk (e.g. a Telegram-bot settings save racing panel shutdown/restart). Stop now flips a mu-guarded `stopped` flag before waiting, and Subscribe checks it under the same lock, so Add and Wait can no longer race. Security: - login_limiter: evictForRoom's fallback eviction picked an arbitrary map key, including ones still under an active cooldown - an attacker flooding /login with fresh usernames could evict their own (or anyone's) blocked record and reset the lockout. The fallback now skips actively-blocked records, only falling back to an unconditional evict if the map is somehow entirely full of active blocks (preserves the hard memory cap). Subscription-endpoint panics (reachable by any client hitting /sub): - internal/sub/service.go: applyPathAndHostParams/Obj (ws/httpupgrade/xhttp with no path settings object) and the TLS alpn readers in three places used unchecked type assertions - exactly the bug classabab7cd0patched elsewhere in the same switch statements, just not these call sites. - internal/sub/json_service.go, clash_service.go: the externalProxy loops in the JSON and Clash generators used unchecked assertions on a legacy/admin-supplied field (missing "port", non-object entry, etc.). - internal/sub/json_service.go: realityData's shortId/serverName selection could assert a non-string array element. Other correctness: - client_traffic.go: ResetAllTraffics (touched by3eb214d0) still skipped clearing NodeClientTraffic node-sync baselines, unlike its sibling reset paths in the same file - a node's next sync would re-add pre-reset delta on top of the freshly-zeroed counter. - inbound_traffic.go: the traffic-tick tx's Commit/Rollback errors were silently discarded; now logged so a backend-level commit failure (e.g. an aborted Postgres tx from a best-effort helper) doesn't masquerade as a successful tick. - outbound_subscription.go: the new subscriptionFetchClient doc comment was wedged between fetchAndStore's existing comment and fetchAndStore itself, leaving fetchAndStore undocumented and the comment describing the wrong function. Convention cleanup: - Removed narrative // comments added by the audit that violate this repo's no-inline-comment rule (mostly narrating the specific bug/fix rather than a lasting contract, and mostly on new Test functions, which this repo's existing tests never comment) - calibrated against this exact codebase's own pre-existing comment style so legitimate godoc-style doc comments were left alone. --------- Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
765 lines
22 KiB
Go
765 lines
22 KiB
Go
package xray
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"os"
|
|
"os/exec"
|
|
"path/filepath"
|
|
"runtime"
|
|
"sort"
|
|
"strings"
|
|
"sync"
|
|
"sync/atomic"
|
|
"syscall"
|
|
"time"
|
|
|
|
"github.com/mhsanaei/3x-ui/v3/internal/config"
|
|
"github.com/mhsanaei/3x-ui/v3/internal/logger"
|
|
"github.com/mhsanaei/3x-ui/v3/internal/util/common"
|
|
)
|
|
|
|
// GetBinaryName returns the Xray binary filename for the current OS and architecture.
|
|
func GetBinaryName() string {
|
|
arch := runtime.GOARCH
|
|
if arch == "arm" {
|
|
arch = "arm32"
|
|
}
|
|
return fmt.Sprintf("xray-%s-%s", runtime.GOOS, arch)
|
|
}
|
|
|
|
// GetBinaryPath returns the full path to the Xray binary executable.
|
|
func GetBinaryPath() string {
|
|
return config.GetBinFolderPath() + "/" + GetBinaryName()
|
|
}
|
|
|
|
// GetConfigPath returns the path to the Xray configuration file in the binary folder.
|
|
func GetConfigPath() string {
|
|
return config.GetBinFolderPath() + "/config.json"
|
|
}
|
|
|
|
// GetGeositePath returns the path to the geosite data file used by Xray.
|
|
func GetGeositePath() string {
|
|
return config.GetBinFolderPath() + "/geosite.dat"
|
|
}
|
|
|
|
// GetGeoipPath returns the path to the geoip data file used by Xray.
|
|
func GetGeoipPath() string {
|
|
return config.GetBinFolderPath() + "/geoip.dat"
|
|
}
|
|
|
|
// GetIPLimitLogPath returns the path to the IP limit log file.
|
|
func GetIPLimitLogPath() string {
|
|
return config.GetLogFolder() + "/3xipl.log"
|
|
}
|
|
|
|
// GetIPLimitBannedLogPath returns the path to the banned IP log file.
|
|
func GetIPLimitBannedLogPath() string {
|
|
return config.GetLogFolder() + "/3xipl-banned.log"
|
|
}
|
|
|
|
// GetIPLimitBannedPrevLogPath returns the path to the previous banned IP log file.
|
|
func GetIPLimitBannedPrevLogPath() string {
|
|
return config.GetLogFolder() + "/3xipl-banned.prev.log"
|
|
}
|
|
|
|
func getLogPath(key string) (string, error) {
|
|
config, err := os.ReadFile(GetConfigPath())
|
|
if err != nil {
|
|
logger.Warningf("Failed to read configuration file: %s", err)
|
|
return "", err
|
|
}
|
|
|
|
jsonConfig := map[string]any{}
|
|
err = json.Unmarshal(config, &jsonConfig)
|
|
if err != nil {
|
|
logger.Warningf("Failed to parse JSON configuration: %s", err)
|
|
return "", err
|
|
}
|
|
|
|
if jsonLog, ok := jsonConfig["log"].(map[string]any); ok {
|
|
if logPath, ok := jsonLog[key].(string); ok {
|
|
return logPath, nil
|
|
}
|
|
}
|
|
return "", err
|
|
}
|
|
|
|
// GetAccessLogPath reads the Xray config and returns the access log file path.
|
|
func GetAccessLogPath() (string, error) {
|
|
return getLogPath("access")
|
|
}
|
|
|
|
// GetErrorLogPath reads the Xray config and returns the error log file path.
|
|
// GetErrorLogPath reads the Xray config and returns the error log file path.
|
|
func GetErrorLogPath() (string, error) {
|
|
return getLogPath("error")
|
|
}
|
|
|
|
// stopProcess calls Stop on the given Process instance.
|
|
func stopProcess(p *Process) {
|
|
_ = p.Stop()
|
|
}
|
|
|
|
// Process wraps an Xray process instance and provides management methods.
|
|
type Process struct {
|
|
*process
|
|
}
|
|
|
|
// NewProcess creates a new Xray process and sets up cleanup on garbage collection.
|
|
func NewProcess(xrayConfig *Config) *Process {
|
|
p := &Process{newProcess(xrayConfig)}
|
|
runtime.SetFinalizer(p, stopProcess)
|
|
return p
|
|
}
|
|
|
|
// NewTestProcess creates a new Xray process that uses a specific config file path.
|
|
// Used for test runs (e.g. outbound test) so the main config.json is not overwritten.
|
|
// The config file at configPath is removed when the process is stopped.
|
|
func NewTestProcess(xrayConfig *Config, configPath string) *Process {
|
|
p := &Process{newTestProcess(xrayConfig, configPath)}
|
|
runtime.SetFinalizer(p, stopProcess)
|
|
return p
|
|
}
|
|
|
|
type process struct {
|
|
// mu guards the process lifecycle fields (cmd, done, exitErr) plus version and
|
|
// apiPort, which are written by Start/startCommand/refreshVersion/refreshAPIPort
|
|
// while being read concurrently by IsRunning/GetErr/GetResult/GetXrayVersion/
|
|
// GetAPIPort/Stop from other goroutines (status endpoint, check-xray-running
|
|
// and traffic jobs). Snapshot under the lock, then do any blocking syscall
|
|
// (Wait/Signal/Kill) on the local copy without holding it.
|
|
mu sync.RWMutex
|
|
cmd *exec.Cmd
|
|
done chan struct{}
|
|
|
|
version string
|
|
apiPort int
|
|
|
|
// onlineClients is the set of emails active on THIS panel's own xray
|
|
// within the online grace window. It is derived only from local xray
|
|
// traffic polls (see RefreshLocalOnline) — never from remote-node
|
|
// snapshots — so a client connected solely to a remote node is not
|
|
// reported online on local inbounds.
|
|
onlineClients []string
|
|
// localActiveInbounds is the set of THIS panel's inbound tags that
|
|
// carried traffic within the same grace window. Xray's user>>>email
|
|
// stat aggregates across every inbound a client is attached to, so an
|
|
// online email alone can't say which inbound it actually used. Pairing
|
|
// it with the inbound>>>tag stat lets the per-inbound view drop a
|
|
// multi-inbound client from inbounds that saw no traffic this window.
|
|
localActiveInbounds []string
|
|
// localLastOnline records, per email, the last time this panel's own
|
|
// xray reported traffic for it. RefreshLocalOnline rebuilds
|
|
// onlineClients from this map each tick, keeping the local online set
|
|
// independent of the shared client_traffics.last_online column — that
|
|
// column is bumped by remote-node syncs too and would otherwise leak
|
|
// remote-only clients into the local set.
|
|
localLastOnline map[string]int64
|
|
// localInboundLastActive mirrors localLastOnline for inbound tags: the
|
|
// last tick this panel's xray reported traffic through each tag.
|
|
// Rebuilt into localActiveInbounds under the same grace window so the
|
|
// two signals stay aligned — an email within grace always has the
|
|
// inbound it used within grace too.
|
|
localInboundLastActive map[string]int64
|
|
// nodeOnlineTrees holds, per direct remote node (keyed by that node's
|
|
// panel-local id), the GUID-keyed online-emails subtree that node
|
|
// reported — its own clients under its panelGuid plus every descendant
|
|
// under theirs. Keying the stored value by GUID (not node id) lets the
|
|
// master attribute a deeply nested client to the node that physically
|
|
// hosts it across a chain (#4983); the outer node-id key is only so a
|
|
// failed probe can drop that whole branch's contribution. NodeTrafficSyncJob
|
|
// populates entries per cron tick and clears them when a probe fails. The
|
|
// mutex guards this map, onlineClients, and localLastOnline above so the
|
|
// online getters never see a torn read.
|
|
nodeOnlineTrees map[int]map[string][]string
|
|
onlineMu sync.RWMutex
|
|
|
|
// onlineAPISupport caches whether the running core implements the
|
|
// online-stats RPCs (GetUsersStats). A new process is created on every
|
|
// restart/version switch, so the flag resets to Unknown and is re-probed
|
|
// lazily by the first caller.
|
|
onlineAPISupport atomic.Int32
|
|
|
|
config *Config
|
|
configPath string // if set, use this path instead of GetConfigPath() and remove on Stop
|
|
logWriter *LogWriter
|
|
exitErr error
|
|
startTime time.Time
|
|
|
|
intentionalStop atomic.Bool
|
|
}
|
|
|
|
// OnlineAPISupport describes whether the running Xray core implements the
|
|
// online-stats API (statsUserOnline + GetUsersStats).
|
|
type OnlineAPISupport int32
|
|
|
|
const (
|
|
// OnlineAPIUnknown means support has not been probed yet for this process.
|
|
OnlineAPIUnknown OnlineAPISupport = iota
|
|
// OnlineAPISupported means the core answered the online-stats RPC.
|
|
OnlineAPISupported
|
|
// OnlineAPIUnsupported means the core returned Unimplemented (older binary).
|
|
OnlineAPIUnsupported
|
|
)
|
|
|
|
// OnlineAPISupport returns the cached online-stats capability of this process.
|
|
func (p *process) OnlineAPISupport() OnlineAPISupport {
|
|
return OnlineAPISupport(p.onlineAPISupport.Load())
|
|
}
|
|
|
|
// SetOnlineAPISupport records the probed online-stats capability of this process.
|
|
func (p *process) SetOnlineAPISupport(v OnlineAPISupport) {
|
|
p.onlineAPISupport.Store(int32(v))
|
|
}
|
|
|
|
var (
|
|
xrayGracefulStopTimeout = 5 * time.Second
|
|
xrayForceStopTimeout = 2 * time.Second
|
|
// OnCrash is called when xray crashes unexpectedly. Set from web layer.
|
|
OnCrash func(err error)
|
|
)
|
|
|
|
// newProcess creates a new internal process struct for Xray.
|
|
func newProcess(config *Config) *process {
|
|
return &process{
|
|
version: "Unknown",
|
|
config: config,
|
|
logWriter: NewLogWriter(),
|
|
startTime: time.Now(),
|
|
}
|
|
}
|
|
|
|
// newTestProcess creates a process that writes and runs with a specific config path.
|
|
func newTestProcess(config *Config, configPath string) *process {
|
|
p := newProcess(config)
|
|
p.configPath = configPath
|
|
return p
|
|
}
|
|
|
|
// IsRunning returns true if the Xray process is currently running.
|
|
func (p *process) IsRunning() bool {
|
|
p.mu.RLock()
|
|
cmd, done := p.cmd, p.done
|
|
p.mu.RUnlock()
|
|
if cmd == nil || cmd.Process == nil {
|
|
return false
|
|
}
|
|
// done is closed by the waitForCommand goroutine exactly when cmd.Wait
|
|
// returns, i.e. when the process has exited; it is the race-free signal here
|
|
// (reading cmd.ProcessState would race with that Wait).
|
|
if done != nil {
|
|
select {
|
|
case <-done:
|
|
return false
|
|
default:
|
|
}
|
|
}
|
|
return true
|
|
}
|
|
|
|
// GetErr returns the last error encountered by the Xray process.
|
|
func (p *process) GetErr() error {
|
|
p.mu.RLock()
|
|
defer p.mu.RUnlock()
|
|
return p.exitErr
|
|
}
|
|
|
|
// GetResult returns the last log line or error from the Xray process.
|
|
func (p *process) GetResult() string {
|
|
p.mu.RLock()
|
|
exitErr := p.exitErr
|
|
p.mu.RUnlock()
|
|
lastLine := p.logWriter.LastLine()
|
|
if len(lastLine) == 0 && exitErr != nil {
|
|
return exitErr.Error()
|
|
}
|
|
return lastLine
|
|
}
|
|
|
|
// GetXrayVersion returns the version string of the Xray process.
|
|
func (p *process) GetXrayVersion() string {
|
|
p.mu.RLock()
|
|
defer p.mu.RUnlock()
|
|
return p.version
|
|
}
|
|
|
|
// GetAPIPort returns the API port used by the Xray process.
|
|
func (p *Process) GetAPIPort() int {
|
|
p.mu.RLock()
|
|
defer p.mu.RUnlock()
|
|
return p.apiPort
|
|
}
|
|
|
|
// GetConfig returns the configuration used by the Xray process.
|
|
func (p *Process) GetConfig() *Config {
|
|
return p.config
|
|
}
|
|
|
|
// SetConfig replaces the stored configuration snapshot after the running
|
|
// process has been reconciled with it through the gRPC API (hot apply), so
|
|
// later change detection compares against what is actually running.
|
|
func (p *Process) SetConfig(config *Config) {
|
|
p.config = config
|
|
}
|
|
|
|
// GetOnlineClients returns the union of locally-online clients and
|
|
// node-online clients from every registered remote panel. Dedupes by
|
|
// email so a client connected to both a local and a node-managed inbound
|
|
// surfaces once. Cheap allocation — typical online sets are small and
|
|
// the union is recomputed on demand.
|
|
func (p *Process) GetOnlineClients() []string {
|
|
p.onlineMu.RLock()
|
|
defer p.onlineMu.RUnlock()
|
|
|
|
if len(p.nodeOnlineTrees) == 0 {
|
|
// Hot path for single-panel deployments: avoid the map+dedupe
|
|
// work entirely and return the local slice as-is.
|
|
return p.onlineClients
|
|
}
|
|
|
|
seen := make(map[string]struct{}, len(p.onlineClients))
|
|
out := make([]string, 0, len(p.onlineClients))
|
|
add := func(emails []string) {
|
|
for _, email := range emails {
|
|
if _, dup := seen[email]; dup {
|
|
continue
|
|
}
|
|
seen[email] = struct{}{}
|
|
out = append(out, email)
|
|
}
|
|
}
|
|
add(p.onlineClients)
|
|
for _, tree := range p.nodeOnlineTrees {
|
|
for _, emails := range tree {
|
|
add(emails)
|
|
}
|
|
}
|
|
return out
|
|
}
|
|
|
|
// GetLocalOnlineClients returns a copy of the emails online on THIS panel's own
|
|
// xray within the grace window. The service layer keys these under the panel's
|
|
// own GUID when assembling the per-node online view.
|
|
func (p *Process) GetLocalOnlineClients() []string {
|
|
p.onlineMu.RLock()
|
|
defer p.onlineMu.RUnlock()
|
|
if len(p.onlineClients) == 0 {
|
|
return nil
|
|
}
|
|
out := make([]string, len(p.onlineClients))
|
|
copy(out, p.onlineClients)
|
|
return out
|
|
}
|
|
|
|
// GetMergedNodeTrees returns the union of every direct node's reported subtree,
|
|
// keyed by the panelGuid of the node that physically hosts each client set.
|
|
// Because each child already reports its descendants under their own GUIDs,
|
|
// merging the direct children yields the whole tree at any depth (#4983), so a
|
|
// client three hops down is attributed to its real node, not the intermediate
|
|
// one. GUIDs are globally unique, but a set reported under the same GUID by more
|
|
// than one path is deduped per key; empty sets are omitted.
|
|
func (p *Process) GetMergedNodeTrees() map[string][]string {
|
|
p.onlineMu.RLock()
|
|
defer p.onlineMu.RUnlock()
|
|
if len(p.nodeOnlineTrees) == 0 {
|
|
return map[string][]string{}
|
|
}
|
|
out := make(map[string][]string)
|
|
seen := make(map[string]map[string]struct{})
|
|
for _, tree := range p.nodeOnlineTrees {
|
|
for guid, emails := range tree {
|
|
if guid == "" || len(emails) == 0 {
|
|
continue
|
|
}
|
|
dedup := seen[guid]
|
|
if dedup == nil {
|
|
dedup = make(map[string]struct{}, len(emails))
|
|
seen[guid] = dedup
|
|
}
|
|
for _, email := range emails {
|
|
if _, ok := dedup[email]; ok {
|
|
continue
|
|
}
|
|
dedup[email] = struct{}{}
|
|
out[guid] = append(out[guid], email)
|
|
}
|
|
}
|
|
}
|
|
return out
|
|
}
|
|
|
|
// GetLocalActiveInbounds returns a copy of THIS panel's inbound tags that
|
|
// carried traffic within the grace window. Only the local xray reports
|
|
// per-inbound activity; remote-node snapshots don't carry it, so the service
|
|
// layer keys these under the panel's own GUID and a node missing from the
|
|
// active-inbounds map means "don't gate" (fall back to the email-only signal).
|
|
func (p *Process) GetLocalActiveInbounds() []string {
|
|
p.onlineMu.RLock()
|
|
defer p.onlineMu.RUnlock()
|
|
if len(p.localActiveInbounds) == 0 {
|
|
return nil
|
|
}
|
|
out := make([]string, len(p.localActiveInbounds))
|
|
copy(out, p.localActiveInbounds)
|
|
return out
|
|
}
|
|
|
|
// RefreshLocalOnline records that each email in activeEmails and each tag in
|
|
// activeInboundTags had local xray traffic at now, then rebuilds onlineClients
|
|
// and localActiveInbounds from every entry seen within graceMs, pruning older
|
|
// ones. Called by the local XrayTrafficJob after each xray gRPC stats poll.
|
|
// Pass nil/empty slices to only prune — NodeTrafficSyncJob does this so a
|
|
// stopped local xray's clients and inbounds still age out between local polls.
|
|
func (p *Process) RefreshLocalOnline(activeEmails, activeInboundTags []string, now, graceMs int64) {
|
|
p.onlineMu.Lock()
|
|
defer p.onlineMu.Unlock()
|
|
if p.localLastOnline == nil {
|
|
p.localLastOnline = make(map[string]int64, len(activeEmails))
|
|
}
|
|
for _, email := range activeEmails {
|
|
p.localLastOnline[email] = now
|
|
}
|
|
online := make([]string, 0, len(p.localLastOnline))
|
|
for email, ts := range p.localLastOnline {
|
|
if now-ts < graceMs {
|
|
online = append(online, email)
|
|
} else {
|
|
delete(p.localLastOnline, email)
|
|
}
|
|
}
|
|
p.onlineClients = online
|
|
|
|
if p.localInboundLastActive == nil {
|
|
p.localInboundLastActive = make(map[string]int64, len(activeInboundTags))
|
|
}
|
|
for _, tag := range activeInboundTags {
|
|
p.localInboundLastActive[tag] = now
|
|
}
|
|
activeInbounds := make([]string, 0, len(p.localInboundLastActive))
|
|
for tag, ts := range p.localInboundLastActive {
|
|
if now-ts < graceMs {
|
|
activeInbounds = append(activeInbounds, tag)
|
|
} else {
|
|
delete(p.localInboundLastActive, tag)
|
|
}
|
|
}
|
|
p.localActiveInbounds = activeInbounds
|
|
}
|
|
|
|
// SetNodeOnlineTree records the GUID-keyed online subtree one direct remote
|
|
// node reported (its own clients under its panelGuid plus every descendant
|
|
// under theirs). Replaces any previous entry for that node — NodeTrafficSyncJob
|
|
// always sends the full subtree per tick.
|
|
func (p *Process) SetNodeOnlineTree(nodeID int, tree map[string][]string) {
|
|
p.onlineMu.Lock()
|
|
defer p.onlineMu.Unlock()
|
|
if p.nodeOnlineTrees == nil {
|
|
p.nodeOnlineTrees = map[int]map[string][]string{}
|
|
}
|
|
p.nodeOnlineTrees[nodeID] = tree
|
|
}
|
|
|
|
// ClearNodeOnlineClients drops a direct node's whole subtree contribution.
|
|
// Called when a probe fails so a downed node — and everything behind it — doesn't
|
|
// keep its clients listed as "online" until the next successful probe.
|
|
func (p *Process) ClearNodeOnlineClients(nodeID int) {
|
|
p.onlineMu.Lock()
|
|
defer p.onlineMu.Unlock()
|
|
delete(p.nodeOnlineTrees, nodeID)
|
|
}
|
|
|
|
// GetUptime returns the uptime of the Xray process in seconds.
|
|
func (p *Process) GetUptime() uint64 {
|
|
return uint64(time.Since(p.startTime).Seconds())
|
|
}
|
|
|
|
// refreshAPIPort updates the API port from the inbound configs.
|
|
func (p *process) refreshAPIPort() {
|
|
port := 0
|
|
for _, inbound := range p.config.InboundConfigs {
|
|
if inbound.Tag == "api" {
|
|
port = inbound.Port
|
|
break
|
|
}
|
|
}
|
|
p.mu.Lock()
|
|
p.apiPort = port
|
|
p.mu.Unlock()
|
|
}
|
|
|
|
// refreshVersion updates the version string by running the Xray binary with -version.
|
|
func (p *process) refreshVersion() {
|
|
version := "Unknown"
|
|
cmd := exec.CommandContext(context.Background(), GetBinaryPath(), "-version")
|
|
if data, err := cmd.Output(); err == nil {
|
|
if datas := bytes.Split(data, []byte(" ")); len(datas) > 1 {
|
|
version = string(datas[1])
|
|
}
|
|
}
|
|
p.mu.Lock()
|
|
p.version = version
|
|
p.mu.Unlock()
|
|
}
|
|
|
|
// Start launches the Xray process with the current configuration.
|
|
func (p *process) Start() (err error) {
|
|
if p.IsRunning() {
|
|
return errors.New("xray is already running")
|
|
}
|
|
|
|
defer func() {
|
|
if err != nil {
|
|
logger.Error("Failure in running xray-core process: ", err)
|
|
p.setExitErr(err)
|
|
}
|
|
}()
|
|
|
|
data, err := json.MarshalIndent(p.config, "", " ")
|
|
if err != nil {
|
|
return common.NewErrorf("Failed to generate XRAY configuration files: %v", err)
|
|
}
|
|
|
|
err = os.MkdirAll(config.GetLogFolder(), 0o770)
|
|
if err != nil {
|
|
logger.Warningf("Failed to create log folder: %s", err)
|
|
}
|
|
|
|
configPath := GetConfigPath()
|
|
if p.configPath != "" {
|
|
configPath = p.configPath
|
|
}
|
|
err = writeFileAtomic(configPath, data, 0o600)
|
|
if err != nil {
|
|
return common.NewErrorf("Failed to write configuration file: %v", err)
|
|
}
|
|
|
|
cmd := exec.CommandContext(context.Background(), GetBinaryPath(), "-c", configPath)
|
|
cmd.Stdout = p.logWriter
|
|
cmd.Stderr = p.logWriter
|
|
|
|
err = p.startCommand(cmd)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
p.refreshVersion()
|
|
p.refreshAPIPort()
|
|
|
|
return nil
|
|
}
|
|
|
|
// writeFileAtomic writes data to path via a same-directory temp file that is
|
|
// permissioned, synced, and renamed into place, so a crash can never leave a
|
|
// partial config; the config holds credentials, hence the 0600 perm. After the
|
|
// rename the parent directory is fsynced to persist the directory entry. That
|
|
// final step is skipped on Windows, where directory fsync is unsupported and
|
|
// os.Rename already uses replace-existing semantics.
|
|
func writeFileAtomic(path string, data []byte, perm os.FileMode) (err error) {
|
|
dir := filepath.Dir(path)
|
|
tmp, err := os.CreateTemp(dir, ".config-*.tmp")
|
|
if err != nil {
|
|
return err
|
|
}
|
|
tmpPath := tmp.Name()
|
|
defer func() {
|
|
_ = tmp.Close()
|
|
if err != nil {
|
|
_ = os.Remove(tmpPath)
|
|
}
|
|
}()
|
|
if err = tmp.Chmod(perm); err != nil {
|
|
return err
|
|
}
|
|
if _, err = tmp.Write(data); err != nil {
|
|
return err
|
|
}
|
|
if err = tmp.Sync(); err != nil {
|
|
return err
|
|
}
|
|
if err = tmp.Close(); err != nil {
|
|
return err
|
|
}
|
|
if err = renameFile(tmpPath, path); err != nil {
|
|
return err
|
|
}
|
|
if runtime.GOOS == "windows" {
|
|
return nil
|
|
}
|
|
dirHandle, err := os.Open(dir)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
err = dirHandle.Sync()
|
|
_ = dirHandle.Close()
|
|
return err
|
|
}
|
|
|
|
var renameFile = os.Rename
|
|
|
|
func (p *process) startCommand(cmd *exec.Cmd) error {
|
|
p.mu.Lock()
|
|
p.cmd = cmd
|
|
p.done = make(chan struct{})
|
|
p.exitErr = nil
|
|
done := p.done
|
|
p.mu.Unlock()
|
|
p.intentionalStop.Store(false)
|
|
|
|
if err := cmd.Start(); err != nil {
|
|
close(done)
|
|
p.mu.Lock()
|
|
p.cmd = nil
|
|
p.mu.Unlock()
|
|
return err
|
|
}
|
|
|
|
attachChildLifetime(cmd)
|
|
|
|
go p.waitForCommand(cmd, done)
|
|
return nil
|
|
}
|
|
|
|
func (p *process) setExitErr(err error) {
|
|
p.mu.Lock()
|
|
p.exitErr = err
|
|
p.mu.Unlock()
|
|
}
|
|
|
|
func (p *process) waitForCommand(cmd *exec.Cmd, done chan struct{}) {
|
|
defer close(done)
|
|
|
|
err := cmd.Wait()
|
|
if err == nil || p.intentionalStop.Load() {
|
|
return
|
|
}
|
|
|
|
// On Windows, killing the process results in "exit status 1" which isn't an error for us.
|
|
if runtime.GOOS == "windows" {
|
|
errStr := strings.ToLower(err.Error())
|
|
if strings.Contains(errStr, "exit status 1") {
|
|
p.setExitErr(err)
|
|
return
|
|
}
|
|
}
|
|
|
|
logger.Error("Failure in running xray-core:", err)
|
|
p.setExitErr(err)
|
|
if OnCrash != nil {
|
|
OnCrash(err)
|
|
}
|
|
}
|
|
|
|
// Stop terminates the running Xray process.
|
|
func (p *process) Stop() error {
|
|
if !p.IsRunning() {
|
|
return errors.New("xray is not running")
|
|
}
|
|
p.intentionalStop.Store(true)
|
|
|
|
// Snapshot cmd once, then run the blocking Signal/Kill/Wait on the local copy
|
|
// without holding the lock.
|
|
p.mu.RLock()
|
|
cmd := p.cmd
|
|
p.mu.RUnlock()
|
|
if cmd == nil || cmd.Process == nil {
|
|
return errors.New("xray is not running")
|
|
}
|
|
|
|
// Remove temporary config file used for test runs so main config is never touched
|
|
if p.configPath != "" {
|
|
if p.configPath != GetConfigPath() {
|
|
// Check if file exists before removing
|
|
if _, err := os.Stat(p.configPath); err == nil {
|
|
_ = os.Remove(p.configPath)
|
|
}
|
|
}
|
|
}
|
|
|
|
if runtime.GOOS == "windows" {
|
|
if err := cmd.Process.Kill(); err != nil && !errors.Is(err, os.ErrProcessDone) {
|
|
return err
|
|
}
|
|
return p.waitForExit(xrayForceStopTimeout)
|
|
}
|
|
|
|
if err := cmd.Process.Signal(syscall.SIGTERM); err != nil {
|
|
if errors.Is(err, os.ErrProcessDone) {
|
|
return p.waitForExit(xrayForceStopTimeout)
|
|
}
|
|
return err
|
|
}
|
|
|
|
if err := p.waitForExit(xrayGracefulStopTimeout); err == nil {
|
|
return nil
|
|
}
|
|
|
|
logger.Warning("xray-core did not stop after SIGTERM, killing process")
|
|
if err := cmd.Process.Kill(); err != nil && !errors.Is(err, os.ErrProcessDone) {
|
|
return err
|
|
}
|
|
return p.waitForExit(xrayForceStopTimeout)
|
|
}
|
|
|
|
func (p *process) waitForExit(timeout time.Duration) error {
|
|
p.mu.RLock()
|
|
done := p.done
|
|
p.mu.RUnlock()
|
|
if done == nil {
|
|
return nil
|
|
}
|
|
|
|
timer := time.NewTimer(timeout)
|
|
defer timer.Stop()
|
|
|
|
select {
|
|
case <-done:
|
|
return nil
|
|
case <-timer.C:
|
|
return common.NewErrorf("timed out waiting for xray-core process to stop after %s", timeout)
|
|
}
|
|
}
|
|
|
|
const (
|
|
crashReportPrefix = "core_crash_"
|
|
crashReportSuffix = ".log"
|
|
maxCrashReports = 10
|
|
)
|
|
|
|
// writeCrashReport persists a captured xray crash chunk to the log folder
|
|
// with nanosecond-precision filename so restart-loop bursts don't overwrite
|
|
// each other, and prunes old reports to keep the folder bounded.
|
|
func writeCrashReport(m []byte) error {
|
|
dir := config.GetLogFolder()
|
|
if err := os.MkdirAll(dir, 0o770); err != nil {
|
|
return err
|
|
}
|
|
pruneOldCrashReports(dir, maxCrashReports-1)
|
|
name := crashReportPrefix + time.Now().Format("20060102_150405_000000000") + crashReportSuffix
|
|
return os.WriteFile(filepath.Join(dir, name), m, 0o640)
|
|
}
|
|
|
|
func pruneOldCrashReports(dir string, keep int) {
|
|
entries, err := os.ReadDir(dir)
|
|
if err != nil {
|
|
return
|
|
}
|
|
var reports []string
|
|
for _, e := range entries {
|
|
n := e.Name()
|
|
if !e.IsDir() && strings.HasPrefix(n, crashReportPrefix) && strings.HasSuffix(n, crashReportSuffix) {
|
|
reports = append(reports, n)
|
|
}
|
|
}
|
|
if len(reports) <= keep {
|
|
return
|
|
}
|
|
sort.Strings(reports)
|
|
for _, old := range reports[:len(reports)-keep] {
|
|
_ = os.Remove(filepath.Join(dir, old))
|
|
}
|
|
}
|