When this code was moved from src/connection.c into src/tls_openssl.c
a return wouldn't break us out from kore_connection_handle() as
previously expected.
This ment that Kore would move the connection into established state
immediately even if SSL_accept() needed to read more.
This broke TLS client authentication as Kore its belts and suspenders
kept throwing a 403 due to the code not properly obtaining the client
certificate when expected.
This work moves all TLS / crypto related code into a tls_openssl.c
file and adds a tls_none.c which contains just stubs.
Allows compilation of Kore with TLS_BACKEND=none to remove building
against OpenSSL.
Also adds code for SHA1/SHA2 taken from openssh-portable so we don't
depend on those being present anymore in libcrypto.
- Make sure tls-alpn01 works even if the underlying SSL library ends up
calling the ALPN callback *before* the SNI extension was parsed and
the correct domain was selected.
LibreSSL still does this, and older OpenSSL did too I believe, however
OpenSSL grew a clue and always makes sure SNI is called first.
Yes, TLS extensions have no fixed order but it still makes sense to
notify applications using your library of the SNI extension first
before anything else almost.
Oh well.
These changes improve the constraint kore had with client authentication and
multiple domains.
- Add kore_x509_subject_name() which will return a C string containing
the x509 subject name in full (in utf8).
- Log TLS errors if client authentication was turned on, will help debug
issues with client authentication in the future.
- If SNI was present in the TLS handshake, check it against the host specified
in the HTTP request and send a 421 in case they mismatch.
- Throw a 403 if client authentication was enabled but no client certificate
was specified.
A new acme process is created that communicates with the acme servers.
This process does not hold any of your private keys (no account keys,
no domain keys etc).
Whenever the acme process requires a signed payload it will ask the keymgr
process to do the signing with the relevant keys.
This process is also sandboxed with pledge+unveil on OpenBSD and seccomp
syscall filtering on Linux.
The implementation only supports the tls-alpn-01 challenge. This means that
you do not need to open additional ports on your machine.
http-01 and dns-01 are currently not supported (no wildcard support).
A new configuration option "acme_provider" is available and can be set
to the acme server its directory. By default this will point to the
live letsencrypt environment:
https://acme-v02.api.letsencrypt.org/directory
The acme process can be controlled via the following config options:
- acme_root (where the acme process will chroot/chdir into).
- acme_runas (the user the acme process will run as).
If none are set, the values from 'root' and 'runas' are taken.
If you want to turn on acme for domains you do it as follows:
domain kore.io {
acme yes
}
You do not need to specify certkey/certfile anymore, if they are present
still
they will be overwritten by the acme system.
The keymgr will store all certificates and keys under its root
(keymgr_root), the account key is stored as "/account-key.pem" and all
obtained certificates go under "certificates/<domain>/fullchain.pem" while
keys go under "certificates/<domain>/key.pem".
Kore will automatically renew certificates if they will expire in 7 days
or less.
Before kore needed to be built with NOTLS=1 to be able to do non TLS
connections. This has been like this for years.
It is time to allow non TLS listeners without having to rebuild Kore.
This commit changes your configuration format and will break existing
applications their config.
Configurations now get listener {} contexts:
listen default {
bind 127.0.0.1 8888
}
The above will create a listener on 127.0.0.1, port 8888 that will serve
TLS (still the default).
If you want to turn off TLS on that listener, specify "tls no" in that
context.
Domains now need to be attached to a listener:
Eg:
domain * {
attach default
}
For the Python API this kills kore.bind(), and kore.bind_unix(). They are
replaced with:
kore.listen("name", ip=None, port=None, path=None, tls=True).
if a crl is expired or not-yet-valid SSL_get_verify_result()
will return these errors too so check for them explicitly
instead of depending on X509_V_OK.
found by @dacechavez
Move away from the parent constantly hitting the disk for every
accesslog the workers are sending.
The workers will now write their own accesslogs to shared
memory before the parent will pick those up. The parent
will flush them to disk once every second or if they grow
larger then 1MB.
This removes the heavy penalty for having access logs
turned on when you are dealing with a large volume
of requests.
This adds kore.proc to the python runtime allowing async processing
handling:
The kore.proc method takes the command to run and an optional timeout
parameter in milliseconds. If the process did not exit normally after
that amount of time a TimeoutError exception is raised.
For instance:
async def run(cmd):
proc = kore.proc(cmd, 1000)
try:
await proc.send("hello")
proc.close_stdin()
except TimeoutError:
proc.kill()
retcode = await proc.reap()
return retcode
Now anyone can schedule events and get a callback to work as long
as the user data structure that is added for the event begins
with a kore_event data structure.
All event state is now kept in that kore_event structure and renamed
CONN_[READ|WRITE]_POSSIBLE to KORE_EVENT_[READ|WRITE].
This commit introduces the ability for the keymgr process
to reload the certificates/keys for domains when receiving
a SIGUSR1 signal.
The keymgr receives 2 new configuration options:
- keymgr_root_path
The root path where the keymgr will live.
If -n is not specified when the application starts the
keymgr process will chroot into here.
- keymgr_runas_user
The user the keymgr will drop privileges towards if
-r was not specified.
All certfile and certkey configuration options are now relative to the
keymgr_root_path configuration setting.
The keymgr process will now also load the certificate for the domain
(rather then the workers) and submit these to the worker processes so
they can be reloaded when required.
Worker processes will refuse connections until the TLS configuration
for a given domain is completed (aka: the workers receive the certificate
for that domain).
Other changes:
- client_certificates renamed to client_verify.
- the chroot configuration option is now called root.
- kore is a little more verbose if privsep options are missing.
- filemaps are now relative to the root configuration option.
A filemap is a way of telling Kore to serve files from a directory
much like a traditional webserver can do.
Kore filemaps only handles files. Kore does not generate directory
indexes or deal with non-regular files.
The way files are sent to a client differs a bit per platform and
build options:
default:
- mmap() backed file transfer due to TLS.
NOTLS=1
- sendfile() under FreeBSD, macOS and Linux.
- mmap() backed file for OpenBSD.
The opened file descriptors/mmap'd regions are cached and reused when
appropriate. If a file is no longer in use it will be closed and evicted
from the cache after 30 seconds.
New API's are available allowing developers to use these facilities via:
void net_send_fileref(struct connection *, struct kore_fileref *);
void http_response_fileref(struct http_request *, struct kore_fileref *);
Kore will attempt to match media types based on file extensions. A few
default types are built-in. Others can be added via the new "http_media_type"
configuration directive.
Do not run the idle timer check for client if it still has a request
queued up. Otherwise if the worker process is very busy you might hit
the timeout even though the client sent us a full request which was queued.
The HTTP layer used to make a copy of each incoming header and its
value for a request. Stop doing that and make HTTP headers zero-copy
all across the board.
This change comes with some api function changes, notably the
http_request_header() function which now takes a const char ** rather
than a char ** out pointer.
This commit also constifies several members of http_request, beware.
Additional rework how the worker processes deal with the accept lock.
Before:
if a worker held the accept lock and it accepted a new connection
it would release the lock for others and back off for 500ms before
attempting to grab the lock again.
This approach worked but under high load this starts becoming obvious.
Now:
- workers not holding the accept lock and not having any connections
will wait less long before returning from kore_platform_event_wait().
- workers not holding the accept lock will no longer blindly wait
an arbitrary amount in kore_platform_event_wait() but will look
at how long until the next lock grab is and base their timeout
on that.
- if a worker its next_lock timeout is up and failed to grab the
lock it will try again in half the time again.
- the worker process holding the lock will when releasing the lock
double check if it still has space for newer connections, if it does
it will keep the lock until it is full. This prevents the lock from
bouncing between several non busy worker processes all the time.
Additional fixes:
- Reduce the number of times we check the timeout list, only do it twice
per second rather then every event tick.
- Fix solo worker count for TLS (we actually hold two processes, not one).
- Make sure we don't accidentally miscalculate the idle time causing new
connections under heavy load to instantly drop.
- Swap from gettimeofday() to clock_gettime() now that MacOS caught up.
- Change pools to use mmap() for allocating regions.
- Change kore_malloc() to use pools for commonly sized objects.
(split into multiple of 2 buckets, starting at 8 bytes up to 8192).
- Rename kore_mem_free() to kore_free().
The preallocated pools will hold up to 128K of elements per block size.
In case a larger object is to be allocated kore_malloc() will use
malloc() instead.