forked from caddyserver/caddy
-
Notifications
You must be signed in to change notification settings - Fork 1
/
handshake.go
305 lines (265 loc) · 10.6 KB
/
handshake.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
package caddytls
import (
"crypto/tls"
"errors"
"fmt"
"log"
"strings"
"sync"
"sync/atomic"
"time"
)
// configGroup is a type that keys configs by their hostname
// (hostnames can have wildcard characters; use the getConfig
// method to get a config by matching its hostname). Its
// GetCertificate function can be used with tls.Config.
type configGroup map[string]*Config
// getConfig gets the config by the first key match for name.
// In other words, "sub.foo.bar" will get the config for "*.foo.bar"
// if that is the closest match. This function MAY return nil
// if no match is found.
//
// This function follows nearly the same logic to lookup
// a hostname as the getCertificate function uses.
func (cg configGroup) getConfig(name string) *Config {
name = strings.ToLower(name)
// exact match? great, let's use it
if config, ok := cg[name]; ok {
return config
}
// try replacing labels in the name with wildcards until we get a match
labels := strings.Split(name, ".")
for i := range labels {
labels[i] = "*"
candidate := strings.Join(labels, ".")
if config, ok := cg[candidate]; ok {
return config
}
}
// as last resort, try a config that serves all names
if config, ok := cg[""]; ok {
return config
}
return nil
}
// GetCertificate gets a certificate to satisfy clientHello. In getting
// the certificate, it abides the rules and settings defined in the
// Config that matches clientHello.ServerName. It first checks the in-
// memory cache, then, if the config enables "OnDemand", it accesses
// disk, then accesses the network if it must obtain a new certificate
// via ACME.
//
// This method is safe for use as a tls.Config.GetCertificate callback.
func (cg configGroup) GetCertificate(clientHello *tls.ClientHelloInfo) (*tls.Certificate, error) {
cert, err := cg.getCertDuringHandshake(strings.ToLower(clientHello.ServerName), true, true)
return &cert.Certificate, err
}
// getCertDuringHandshake will get a certificate for name. It first tries
// the in-memory cache. If no certificate for name is in the cache, the
// config most closely corresponding to name will be loaded. If that config
// allows it (OnDemand==true) and if loadIfNecessary == true, it goes to disk
// to load it into the cache and serve it. If it's not on disk and if
// obtainIfNecessary == true, the certificate will be obtained from the CA,
// cached, and served. If obtainIfNecessary is true, then loadIfNecessary
// must also be set to true. An error will be returned if and only if no
// certificate is available.
//
// This function is safe for concurrent use.
func (cg configGroup) getCertDuringHandshake(name string, loadIfNecessary, obtainIfNecessary bool) (Certificate, error) {
// First check our in-memory cache to see if we've already loaded it
cert, matched, defaulted := getCertificate(name)
if matched {
return cert, nil
}
// Get the relevant TLS config for this name. If OnDemand is enabled,
// then we might be able to load or obtain a needed certificate.
cfg := cg.getConfig(name)
if cfg != nil && cfg.OnDemand && loadIfNecessary {
// Then check to see if we have one on disk
loadedCert, err := CacheManagedCertificate(name, cfg)
if err == nil {
loadedCert, err = cg.handshakeMaintenance(name, loadedCert)
if err != nil {
log.Printf("[ERROR] Maintaining newly-loaded certificate for %s: %v", name, err)
}
return loadedCert, nil
}
if obtainIfNecessary {
// By this point, we need to ask the CA for a certificate
name = strings.ToLower(name)
// Make sure aren't over any applicable limits
err := cg.checkLimitsForObtainingNewCerts(name, cfg)
if err != nil {
return Certificate{}, err
}
// Name has to qualify for a certificate
if !HostQualifies(name) {
return cert, errors.New("hostname '" + name + "' does not qualify for certificate")
}
// Obtain certificate from the CA
return cg.obtainOnDemandCertificate(name, cfg)
}
}
// Fall back to the default certificate if there is one
if defaulted {
return cert, nil
}
return Certificate{}, fmt.Errorf("no certificate available for %s", name)
}
// checkLimitsForObtainingNewCerts checks to see if name can be issued right
// now according to mitigating factors we keep track of and preferences the
// user has set. If a non-nil error is returned, do not issue a new certificate
// for name.
func (cg configGroup) checkLimitsForObtainingNewCerts(name string, cfg *Config) error {
// User can set hard limit for number of certs for the process to issue
if cfg.OnDemandState.MaxObtain > 0 &&
atomic.LoadInt32(&cfg.OnDemandState.ObtainedCount) >= cfg.OnDemandState.MaxObtain {
return fmt.Errorf("%s: maximum certificates issued (%d)", name, cfg.OnDemandState.MaxObtain)
}
// Make sure name hasn't failed a challenge recently
failedIssuanceMu.RLock()
when, ok := failedIssuance[name]
failedIssuanceMu.RUnlock()
if ok {
return fmt.Errorf("%s: throttled; refusing to issue cert since last attempt on %s failed", name, when.String())
}
// Make sure, if we've issued a few certificates already, that we haven't
// issued any recently
lastIssueTimeMu.Lock()
since := time.Since(lastIssueTime)
lastIssueTimeMu.Unlock()
if atomic.LoadInt32(&cfg.OnDemandState.ObtainedCount) >= 10 && since < 10*time.Minute {
return fmt.Errorf("%s: throttled; last certificate was obtained %v ago", name, since)
}
// 👍Good to go
return nil
}
// obtainOnDemandCertificate obtains a certificate for name for the given
// name. If another goroutine has already started obtaining a cert for
// name, it will wait and use what the other goroutine obtained.
//
// This function is safe for use by multiple concurrent goroutines.
func (cg configGroup) obtainOnDemandCertificate(name string, cfg *Config) (Certificate, error) {
// We must protect this process from happening concurrently, so synchronize.
obtainCertWaitChansMu.Lock()
wait, ok := obtainCertWaitChans[name]
if ok {
// lucky us -- another goroutine is already obtaining the certificate.
// wait for it to finish obtaining the cert and then we'll use it.
obtainCertWaitChansMu.Unlock()
<-wait
return cg.getCertDuringHandshake(name, true, false)
}
// looks like it's up to us to do all the work and obtain the cert.
// make a chan others can wait on if needed
wait = make(chan struct{})
obtainCertWaitChans[name] = wait
obtainCertWaitChansMu.Unlock()
// do the obtain
log.Printf("[INFO] Obtaining new certificate for %s", name)
err := cfg.ObtainCert(name, false)
// immediately unblock anyone waiting for it; doing this in
// a defer would risk deadlock because of the recursive call
// to getCertDuringHandshake below when we return!
obtainCertWaitChansMu.Lock()
close(wait)
delete(obtainCertWaitChans, name)
obtainCertWaitChansMu.Unlock()
if err != nil {
// Failed to solve challenge, so don't allow another on-demand
// issue for this name to be attempted for a little while.
failedIssuanceMu.Lock()
failedIssuance[name] = time.Now()
go func(name string) {
time.Sleep(5 * time.Minute)
failedIssuanceMu.Lock()
delete(failedIssuance, name)
failedIssuanceMu.Unlock()
}(name)
failedIssuanceMu.Unlock()
return Certificate{}, err
}
// Success - update counters and stuff
atomic.AddInt32(&cfg.OnDemandState.ObtainedCount, 1)
lastIssueTimeMu.Lock()
lastIssueTime = time.Now()
lastIssueTimeMu.Unlock()
// certificate is already on disk; now just start over to load it and serve it
return cg.getCertDuringHandshake(name, true, false)
}
// handshakeMaintenance performs a check on cert for expiration and OCSP
// validity.
//
// This function is safe for use by multiple concurrent goroutines.
func (cg configGroup) handshakeMaintenance(name string, cert Certificate) (Certificate, error) {
// Check cert expiration
timeLeft := cert.NotAfter.Sub(time.Now().UTC())
if timeLeft < RenewDurationBefore {
log.Printf("[INFO] Certificate for %v expires in %v; attempting renewal", cert.Names, timeLeft)
return cg.renewDynamicCertificate(name, cert.Config)
}
// Check OCSP staple validity
if cert.OCSP != nil {
refreshTime := cert.OCSP.ThisUpdate.Add(cert.OCSP.NextUpdate.Sub(cert.OCSP.ThisUpdate) / 2)
if time.Now().After(refreshTime) {
err := stapleOCSP(&cert, nil)
if err != nil {
// An error with OCSP stapling is not the end of the world, and in fact, is
// quite common considering not all certs have issuer URLs that support it.
log.Printf("[ERROR] Getting OCSP for %s: %v", name, err)
}
certCacheMu.Lock()
certCache[name] = cert
certCacheMu.Unlock()
}
}
return cert, nil
}
// renewDynamicCertificate renews the certificate for name using cfg. It returns the
// certificate to use and an error, if any. currentCert may be returned even if an
// error occurs, since we perform renewals before they expire and it may still be
// usable. name should already be lower-cased before calling this function.
//
// This function is safe for use by multiple concurrent goroutines.
func (cg configGroup) renewDynamicCertificate(name string, cfg *Config) (Certificate, error) {
obtainCertWaitChansMu.Lock()
wait, ok := obtainCertWaitChans[name]
if ok {
// lucky us -- another goroutine is already renewing the certificate.
// wait for it to finish, then we'll use the new one.
obtainCertWaitChansMu.Unlock()
<-wait
return cg.getCertDuringHandshake(name, true, false)
}
// looks like it's up to us to do all the work and renew the cert
wait = make(chan struct{})
obtainCertWaitChans[name] = wait
obtainCertWaitChansMu.Unlock()
// do the renew
log.Printf("[INFO] Renewing certificate for %s", name)
err := cfg.RenewCert(name, false)
// immediately unblock anyone waiting for it; doing this in
// a defer would risk deadlock because of the recursive call
// to getCertDuringHandshake below when we return!
obtainCertWaitChansMu.Lock()
close(wait)
delete(obtainCertWaitChans, name)
obtainCertWaitChansMu.Unlock()
if err != nil {
return Certificate{}, err
}
return cg.getCertDuringHandshake(name, true, false)
}
// obtainCertWaitChans is used to coordinate obtaining certs for each hostname.
var obtainCertWaitChans = make(map[string]chan struct{})
var obtainCertWaitChansMu sync.Mutex
// failedIssuance is a set of names that we recently failed to get a
// certificate for from the ACME CA. They are removed after some time.
// When a name is in this map, do not issue a certificate for it on-demand.
var failedIssuance = make(map[string]time.Time)
var failedIssuanceMu sync.RWMutex
// lastIssueTime records when we last obtained a certificate successfully.
// If this value is recent, do not make any on-demand certificate requests.
var lastIssueTime time.Time
var lastIssueTimeMu sync.Mutex
var errNoCert = errors.New("no certificate available")