forgejo/services/webhook/deliver.go

329 lines
9.8 KiB
Go
Raw Normal View History

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package webhook
import (
"context"
"crypto/hmac"
"crypto/sha1"
[GITEA] Drop sha256-simd in favor of stdlib - In Go 1.21 the crypto/sha256 [got a massive improvement](https://go.dev/doc/go1.21#crypto/sha256) by utilizing the SHA instructions for AMD64 CPUs, which sha256-simd already was doing. The performance is now on par and I think it's preferable to use the standard library rather than a package when possible. ``` cpu: AMD Ryzen 5 3600X 6-Core Processor │ simd.txt │ go.txt │ │ sec/op │ sec/op vs base │ Hash/8Bytes-12 63.25n ± 1% 73.38n ± 1% +16.02% (p=0.002 n=6) Hash/64Bytes-12 98.73n ± 1% 105.30n ± 1% +6.65% (p=0.002 n=6) Hash/1K-12 567.2n ± 1% 572.8n ± 1% +0.99% (p=0.002 n=6) Hash/8K-12 4.062µ ± 1% 4.062µ ± 1% ~ (p=0.396 n=6) Hash/1M-12 512.1µ ± 0% 510.6µ ± 1% ~ (p=0.485 n=6) Hash/5M-12 2.556m ± 1% 2.564m ± 0% ~ (p=0.093 n=6) Hash/10M-12 5.112m ± 0% 5.127m ± 0% ~ (p=0.093 n=6) geomean 13.82µ 14.27µ +3.28% │ simd.txt │ go.txt │ │ B/s │ B/s vs base │ Hash/8Bytes-12 120.6Mi ± 1% 104.0Mi ± 1% -13.81% (p=0.002 n=6) Hash/64Bytes-12 618.2Mi ± 1% 579.8Mi ± 1% -6.22% (p=0.002 n=6) Hash/1K-12 1.682Gi ± 1% 1.665Gi ± 1% -0.98% (p=0.002 n=6) Hash/8K-12 1.878Gi ± 1% 1.878Gi ± 1% ~ (p=0.310 n=6) Hash/1M-12 1.907Gi ± 0% 1.913Gi ± 1% ~ (p=0.485 n=6) Hash/5M-12 1.911Gi ± 1% 1.904Gi ± 0% ~ (p=0.093 n=6) Hash/10M-12 1.910Gi ± 0% 1.905Gi ± 0% ~ (p=0.093 n=6) geomean 1.066Gi 1.032Gi -3.18% ``` (cherry picked from commit abd94ff5b59c86e793fd9bf12187ea6cfd1f3fa1) (cherry picked from commit 15e81637abf70576a564cf9eecaa9640228afb5b) Conflicts: go.mod https://codeberg.org/forgejo/forgejo/pulls/1581 (cherry picked from commit 325d92917f655c999b81b08832ee623d6b669f0f) Conflicts: modules/context/context_cookie.go https://codeberg.org/forgejo/forgejo/pulls/1617 (cherry picked from commit 358819e8959886faa171ac16541097500d0a703e) (cherry picked from commit 362fd7aae17832fa922fa017794bc564ca43060d) (cherry picked from commit 4f64ee294ee05c93042b6ec68f0a179ec249dab9) (cherry picked from commit 4bde77f7b13c5f961c141c01b6da1f9eda5ec387) (cherry picked from commit 1311e30a811675eb623692349e4e808a85aabef6) (cherry picked from commit 57b69e334c2973118488b9b5dbdc8a2c88135756) (cherry picked from commit 52dc892fadecf39e89c3c351edc9efb42522257b) (cherry picked from commit 77f54f4187869c6eabcc837742fd3f908093a76c) (cherry picked from commit 0d0392f3a510ce3683bb649dee1e65b45dd91354) Conflicts: go.mod https://codeberg.org/forgejo/forgejo/pulls/2034 (cherry picked from commit 92798364e8fe3188a2100b54f3adea943f8309e9) (cherry picked from commit 43d218127752aa9251c4c3ef71b9c060f109dffc) (cherry picked from commit 45c88b86a35729fc0b2dc6b72bc33caf9f69265f) (cherry picked from commit a1cd6f4e3a7956773cbc0aef8abb80d17b62eb49) (cherry picked from commit 01191dc2adf8c57ae448be37e73158005a8ff74d) (cherry picked from commit 151e07f37e2854ad633f1352fb0ce3cd06f4b2ae)
2023-09-30 00:45:31 +02:00
"crypto/sha256"
"crypto/tls"
"encoding/hex"
"fmt"
"io"
"net/http"
"net/url"
"strings"
"sync"
"time"
webhook_model "code.gitea.io/gitea/models/webhook"
"code.gitea.io/gitea/modules/graceful"
"code.gitea.io/gitea/modules/hostmatcher"
"code.gitea.io/gitea/modules/log"
"code.gitea.io/gitea/modules/process"
"code.gitea.io/gitea/modules/proxy"
"code.gitea.io/gitea/modules/queue"
"code.gitea.io/gitea/modules/setting"
"code.gitea.io/gitea/modules/timeutil"
webhook_module "code.gitea.io/gitea/modules/webhook"
"github.com/gobwas/glob"
)
// Deliver deliver hook task
func Deliver(ctx context.Context, t *webhook_model.HookTask) error {
w, err := webhook_model.GetWebhookByID(ctx, t.HookID)
if err != nil {
return err
}
defer func() {
err := recover()
if err == nil {
return
}
// There was a panic whilst delivering a hook...
log.Error("PANIC whilst trying to deliver webhook task[%d] to webhook %s Panic: %v\nStacktrace: %s", t.ID, w.URL, err, log.Stack(2))
}()
t.IsDelivered = true
var req *http.Request
switch w.HTTPMethod {
case "":
log.Info("HTTP Method for webhook %s empty, setting to POST as default", w.URL)
fallthrough
case http.MethodPost:
switch w.ContentType {
case webhook_model.ContentTypeJSON:
req, err = http.NewRequest("POST", w.URL, strings.NewReader(t.PayloadContent))
if err != nil {
return err
}
req.Header.Set("Content-Type", "application/json")
case webhook_model.ContentTypeForm:
forms := url.Values{
"payload": []string{t.PayloadContent},
}
req, err = http.NewRequest("POST", w.URL, strings.NewReader(forms.Encode()))
if err != nil {
return err
}
req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
}
case http.MethodGet:
u, err := url.Parse(w.URL)
if err != nil {
return fmt.Errorf("unable to deliver webhook task[%d] as cannot parse webhook url %s: %w", t.ID, w.URL, err)
}
vals := u.Query()
vals["payload"] = []string{t.PayloadContent}
u.RawQuery = vals.Encode()
req, err = http.NewRequest("GET", u.String(), nil)
if err != nil {
return fmt.Errorf("unable to deliver webhook task[%d] as unable to create HTTP request for webhook url %s: %w", t.ID, w.URL, err)
}
case http.MethodPut:
switch w.Type {
case webhook_module.MATRIX:
Add Webhook authorization header (#20926) _This is a different approach to #20267, I took the liberty of adapting some parts, see below_ ## Context In some cases, a weebhook endpoint requires some kind of authentication. The usual way is by sending a static `Authorization` header, with a given token. For instance: - Matrix expects a `Bearer <token>` (already implemented, by storing the header cleartext in the metadata - which is buggy on retry #19872) - TeamCity #18667 - Gitea instances #20267 - SourceHut https://man.sr.ht/graphql.md#authentication-strategies (this is my actual personal need :) ## Proposed solution Add a dedicated encrypt column to the webhook table (instead of storing it as meta as proposed in #20267), so that it gets available for all present and future hook types (especially the custom ones #19307). This would also solve the buggy matrix retry #19872. As a first step, I would recommend focusing on the backend logic and improve the frontend at a later stage. For now the UI is a simple `Authorization` field (which could be later customized with `Bearer` and `Basic` switches): ![2022-08-23-142911](https://user-images.githubusercontent.com/3864879/186162483-5b721504-eef5-4932-812e-eb96a68494cc.png) The header name is hard-coded, since I couldn't fine any usecase justifying otherwise. ## Questions - What do you think of this approach? @justusbunsi @Gusted @silverwind - ~~How are the migrations generated? Do I have to manually create a new file, or is there a command for that?~~ - ~~I started adding it to the API: should I complete it or should I drop it? (I don't know how much the API is actually used)~~ ## Done as well: - add a migration for the existing matrix webhooks and remove the `Authorization` logic there _Closes #19872_ Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com> Co-authored-by: Gusted <williamzijl7@hotmail.com> Co-authored-by: delvh <dev.lh@web.de>
2022-11-03 19:23:20 +01:00
txnID, err := getMatrixTxnID([]byte(t.PayloadContent))
if err != nil {
return err
}
url := fmt.Sprintf("%s/%s", w.URL, url.PathEscape(txnID))
req, err = http.NewRequest("PUT", url, strings.NewReader(t.PayloadContent))
if err != nil {
return fmt.Errorf("unable to deliver webhook task[%d] as cannot create matrix request for webhook url %s: %w", t.ID, w.URL, err)
}
default:
return fmt.Errorf("invalid http method for webhook task[%d] in webhook %s: %v", t.ID, w.URL, w.HTTPMethod)
}
default:
return fmt.Errorf("invalid http method for webhook task[%d] in webhook %s: %v", t.ID, w.URL, w.HTTPMethod)
}
var signatureSHA1 string
var signatureSHA256 string
if len(w.Secret) > 0 {
sig1 := hmac.New(sha1.New, []byte(w.Secret))
sig256 := hmac.New(sha256.New, []byte(w.Secret))
_, err = io.MultiWriter(sig1, sig256).Write([]byte(t.PayloadContent))
if err != nil {
log.Error("prepareWebhooks.sigWrite: %v", err)
}
signatureSHA1 = hex.EncodeToString(sig1.Sum(nil))
signatureSHA256 = hex.EncodeToString(sig256.Sum(nil))
}
event := t.EventType.Event()
eventType := string(t.EventType)
req.Header.Add("X-Gitea-Delivery", t.UUID)
req.Header.Add("X-Gitea-Event", event)
req.Header.Add("X-Gitea-Event-Type", eventType)
req.Header.Add("X-Gitea-Signature", signatureSHA256)
req.Header.Add("X-Gogs-Delivery", t.UUID)
req.Header.Add("X-Gogs-Event", event)
req.Header.Add("X-Gogs-Event-Type", eventType)
req.Header.Add("X-Gogs-Signature", signatureSHA256)
req.Header.Add("X-Hub-Signature", "sha1="+signatureSHA1)
req.Header.Add("X-Hub-Signature-256", "sha256="+signatureSHA256)
req.Header["X-GitHub-Delivery"] = []string{t.UUID}
req.Header["X-GitHub-Event"] = []string{event}
req.Header["X-GitHub-Event-Type"] = []string{eventType}
Add Webhook authorization header (#20926) _This is a different approach to #20267, I took the liberty of adapting some parts, see below_ ## Context In some cases, a weebhook endpoint requires some kind of authentication. The usual way is by sending a static `Authorization` header, with a given token. For instance: - Matrix expects a `Bearer <token>` (already implemented, by storing the header cleartext in the metadata - which is buggy on retry #19872) - TeamCity #18667 - Gitea instances #20267 - SourceHut https://man.sr.ht/graphql.md#authentication-strategies (this is my actual personal need :) ## Proposed solution Add a dedicated encrypt column to the webhook table (instead of storing it as meta as proposed in #20267), so that it gets available for all present and future hook types (especially the custom ones #19307). This would also solve the buggy matrix retry #19872. As a first step, I would recommend focusing on the backend logic and improve the frontend at a later stage. For now the UI is a simple `Authorization` field (which could be later customized with `Bearer` and `Basic` switches): ![2022-08-23-142911](https://user-images.githubusercontent.com/3864879/186162483-5b721504-eef5-4932-812e-eb96a68494cc.png) The header name is hard-coded, since I couldn't fine any usecase justifying otherwise. ## Questions - What do you think of this approach? @justusbunsi @Gusted @silverwind - ~~How are the migrations generated? Do I have to manually create a new file, or is there a command for that?~~ - ~~I started adding it to the API: should I complete it or should I drop it? (I don't know how much the API is actually used)~~ ## Done as well: - add a migration for the existing matrix webhooks and remove the `Authorization` logic there _Closes #19872_ Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com> Co-authored-by: Gusted <williamzijl7@hotmail.com> Co-authored-by: delvh <dev.lh@web.de>
2022-11-03 19:23:20 +01:00
// Add Authorization Header
authorization, err := w.HeaderAuthorization()
if err != nil {
log.Error("Webhook could not get Authorization header [%d]: %v", w.ID, err)
return err
}
if authorization != "" {
req.Header["Authorization"] = []string{authorization}
}
// Record delivery information.
t.RequestInfo = &webhook_model.HookRequest{
URL: req.URL.String(),
HTTPMethod: req.Method,
Headers: map[string]string{},
}
for k, vals := range req.Header {
t.RequestInfo.Headers[k] = strings.Join(vals, ",")
}
t.ResponseInfo = &webhook_model.HookResponse{
Headers: map[string]string{},
}
// OK We're now ready to attempt to deliver the task - we must double check that it
// has not been delivered in the meantime
updated, err := webhook_model.MarkTaskDelivered(ctx, t)
if err != nil {
log.Error("MarkTaskDelivered[%d]: %v", t.ID, err)
return fmt.Errorf("unable to mark task[%d] delivered in the db: %w", t.ID, err)
}
if !updated {
// This webhook task has already been attempted to be delivered or is in the process of being delivered
log.Trace("Webhook Task[%d] already delivered", t.ID)
return nil
}
// All code from this point will update the hook task
defer func() {
t.Delivered = timeutil.TimeStampNanoNow()
if t.IsSucceed {
log.Trace("Hook delivered: %s", t.UUID)
} else if !w.IsActive {
log.Trace("Hook delivery skipped as webhook is inactive: %s", t.UUID)
} else {
log.Trace("Hook delivery failed: %s", t.UUID)
}
if err := webhook_model.UpdateHookTask(ctx, t); err != nil {
log.Error("UpdateHookTask [%d]: %v", t.ID, err)
}
// Update webhook last delivery status.
if t.IsSucceed {
w.LastStatus = webhook_module.HookStatusSucceed
} else {
w.LastStatus = webhook_module.HookStatusFail
}
if err = webhook_model.UpdateWebhookLastStatus(ctx, w); err != nil {
log.Error("UpdateWebhookLastStatus: %v", err)
return
}
}()
if setting.DisableWebhooks {
return fmt.Errorf("webhook task skipped (webhooks disabled): [%d]", t.ID)
}
if !w.IsActive {
log.Trace("Webhook %s in Webhook Task[%d] is not active", w.URL, t.ID)
return nil
}
resp, err := webhookHTTPClient.Do(req.WithContext(ctx))
if err != nil {
t.ResponseInfo.Body = fmt.Sprintf("Delivery: %v", err)
return fmt.Errorf("unable to deliver webhook task[%d] in %s due to error in http client: %w", t.ID, w.URL, err)
}
defer resp.Body.Close()
// Status code is 20x can be seen as succeed.
t.IsSucceed = resp.StatusCode/100 == 2
t.ResponseInfo.Status = resp.StatusCode
for k, vals := range resp.Header {
t.ResponseInfo.Headers[k] = strings.Join(vals, ",")
}
p, err := io.ReadAll(resp.Body)
if err != nil {
t.ResponseInfo.Body = fmt.Sprintf("read body: %s", err)
return fmt.Errorf("unable to deliver webhook task[%d] in %s as unable to read response body: %w", t.ID, w.URL, err)
}
t.ResponseInfo.Body = string(p)
return nil
}
var (
webhookHTTPClient *http.Client
once sync.Once
hostMatchers []glob.Glob
)
func webhookProxy(allowList *hostmatcher.HostMatchList) func(req *http.Request) (*url.URL, error) {
if setting.Webhook.ProxyURL == "" {
return proxy.Proxy()
}
once.Do(func() {
for _, h := range setting.Webhook.ProxyHosts {
if g, err := glob.Compile(h); err == nil {
hostMatchers = append(hostMatchers, g)
} else {
log.Error("glob.Compile %s failed: %v", h, err)
}
}
})
return func(req *http.Request) (*url.URL, error) {
for _, v := range hostMatchers {
if v.Match(req.URL.Host) {
if !allowList.MatchHostName(req.URL.Host) {
return nil, fmt.Errorf("webhook can only call allowed HTTP servers (check your %s setting), deny '%s'", allowList.SettingKeyHint, req.URL.Host)
}
return http.ProxyURL(setting.Webhook.ProxyURLFixed)(req)
}
}
return http.ProxyFromEnvironment(req)
}
}
// Init starts the hooks delivery thread
func Init() error {
timeout := time.Duration(setting.Webhook.DeliverTimeout) * time.Second
allowedHostListValue := setting.Webhook.AllowedHostList
if allowedHostListValue == "" {
allowedHostListValue = hostmatcher.MatchBuiltinExternal
}
allowedHostMatcher := hostmatcher.ParseHostMatchList("webhook.ALLOWED_HOST_LIST", allowedHostListValue)
webhookHTTPClient = &http.Client{
Timeout: timeout,
Transport: &http.Transport{
TLSClientConfig: &tls.Config{InsecureSkipVerify: setting.Webhook.SkipTLSVerify},
Proxy: webhookProxy(allowedHostMatcher),
DialContext: hostmatcher.NewDialContextWithProxy("webhook", allowedHostMatcher, nil, setting.Webhook.ProxyURLFixed),
},
}
hookQueue = queue.CreateUniqueQueue(graceful.GetManager().ShutdownContext(), "webhook_sender", handler)
if hookQueue == nil {
return fmt.Errorf("unable to create webhook_sender queue")
}
go graceful.GetManager().RunWithCancel(hookQueue)
go graceful.GetManager().RunWithShutdownContext(populateWebhookSendingQueue)
return nil
}
func populateWebhookSendingQueue(ctx context.Context) {
ctx, _, finished := process.GetManager().AddContext(ctx, "Webhook: Populate sending queue")
defer finished()
lowerID := int64(0)
for {
taskIDs, err := webhook_model.FindUndeliveredHookTaskIDs(ctx, lowerID)
if err != nil {
log.Error("Unable to populate webhook queue as FindUndeliveredHookTaskIDs failed: %v", err)
return
}
if len(taskIDs) == 0 {
return
}
lowerID = taskIDs[len(taskIDs)-1]
for _, taskID := range taskIDs {
select {
case <-ctx.Done():
log.Warn("Shutdown before Webhook Sending queue finishing being populated")
return
default:
}
if err := enqueueHookTask(taskID); err != nil {
log.Error("Unable to push HookTask[%d] to the Webhook Sending queue: %v", taskID, err)
}
}
}
}