Merge pull request #16238 from Security-Onion-Solutions/hotfix/3.3.0

Hotfix/3.3.0

.github/DISCUSSION_TEMPLATE/3-0.yml

@@ -13,8 +13,6 @@ body:
         - 3.1.0
         - 3.2.0
         - 3.3.0
-        - 3.4.0
-        - 3.5.0
         - Other (please provide detail below)
     validations:
       required: true

.github/workflows/pythontest.yml

@@ -6,10 +6,6 @@ on:
       - "salt/sensoroni/files/analyzers/**"
       - "salt/manager/tools/sbin/**"
       - "salt/_beacons/**"
-      - "salt/elastalert/files/modules/**"
-      - "salt/telegraf/tools/sbin_jinja/**"
-      - "salt/telegraf/defaults.yaml"
-      - "salt/telegraf/soc_telegraf.yaml"
 
 jobs:
   build:
@@ -19,7 +15,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.14"]
-        python-code-path: ["salt/sensoroni/files/analyzers", "salt/manager/tools/sbin", "salt/_beacons", "salt/elastalert/files/modules/so"]
+        python-code-path: ["salt/sensoroni/files/analyzers", "salt/manager/tools/sbin", "salt/_beacons"]
 
     steps:
     - uses: actions/checkout@v3
@@ -38,25 +34,3 @@ jobs:
     - name: Test with pytest
       run: |
         PYTHONPATH=${{ matrix.python-code-path }} pytest ${{ matrix.python-code-path }} --cov=${{ matrix.python-code-path }} --doctest-modules --cov-report=term --cov-fail-under=100 --cov-config=pytest.ini
-
-  telegraf-collector:
-    # so-container-stats is a jinja template rather than an importable module, so it gets its
-    # own job: the test renders it the way salt does, then drives it with a faked docker engine
-    # and cgroup tree. No container runtime is needed.
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v3
-    - name: Set up Python
-      uses: actions/setup-python@v3
-      with:
-        python-version: "3.14"
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        python -m pip install flake8 pytest jinja2 pyyaml
-    - name: Lint with flake8
-      run: |
-        flake8 salt/telegraf/tools/sbin_jinja/so-container-stats_test.py --config=pytest.ini
-    - name: Test with pytest
-      run: |
-        pytest salt/telegraf/tools/sbin_jinja/so-container-stats_test.py -v

DOWNLOAD_AND_VERIFY_ISO.md

@@ -1,17 +1,17 @@
-### 3.4.0-20261102 ISO image released on 2026/11/02
+### 3.3.0-20260911 ISO image released on 2026/09/11
 
 
 ### Download and Verify
 
-3.4.0-20261102 ISO image:  
-https://download.securityonion.net/file/securityonion/securityonion-3.4.0-20261102.iso
+3.3.0-20260911 ISO image:  
+https://download.securityonion.net/file/securityonion/securityonion-3.3.0-20260911.iso
  
-MD5: FB0380AE996E175D6CC7E7A35D8CC178  
-SHA1: D8960F1DA352710BCA209773BF0B3AE8791D0D1B  
-SHA256: DFC4C87668836852A328EC7A0B755C8C1511FF0E43D423DEE23047A95F676D99  
+MD5: 12B18433D3A2198A185892FF79CF638F  
+SHA1: 2B3C2E1FA7A78ED1F956E7EDCC12E32593C14EEE  
+SHA256: 0938C73B76CE30EC9E4394D312C79EA7CAC721B6818541697279A6221F7D870D  
 
 Signature for ISO image:  
-https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.4.0-20261102.iso.sig
+https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.3.0-20260911.iso.sig
 
 Signing key:  
 https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/main/KEYS  
@@ -25,22 +25,22 @@ wget https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/
 
 Download the signature file for the ISO:  
 ```
-wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.4.0-20261102.iso.sig
+wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.3.0-20260911.iso.sig
 ```
 
 Download the ISO image:  
 ```
-wget https://download.securityonion.net/file/securityonion/securityonion-3.4.0-20261102.iso
+wget https://download.securityonion.net/file/securityonion/securityonion-3.3.0-20260911.iso
 ```
 
 Verify the downloaded ISO image using the signature file:  
 ```
-gpg --verify securityonion-3.4.0-20261102.iso.sig securityonion-3.4.0-20261102.iso
+gpg --verify securityonion-3.3.0-20260911.iso.sig securityonion-3.3.0-20260911.iso
 ```
 
 The output should show "Good signature" and the Primary key fingerprint should match what's shown below:
 ```
-gpg: Signature made Sat 31 Oct 2026 09:27:50 AM EDT using RSA key ID FE507013
+gpg: Signature made Fri 11 Sep 2026 11:23:56 AM EDT using RSA key ID FE507013
 gpg: Good signature from "Security Onion Solutions, LLC <info@securityonionsolutions.com>"
 gpg: WARNING: This key is not certified with a trusted signature!
 gpg:          There is no indication that the signature belongs to the owner.

HOTFIX

@@ -1 +1 @@
-
+20260911

VERSION

@@ -1 +1 @@
-3.5.0
+3.3.0

salt/ca/files/blocklist/emsign-ecc-root-ca-c3.pem

@@ -1,14 +0,0 @@
------BEGIN CERTIFICATE-----
-MIICKzCCAbGgAwIBAgIKe3G2gla4EnycqDAKBggqhkjOPQQDAzBaMQswCQYDVQQG
-EwJVUzETMBEGA1UECxMKZW1TaWduIFBLSTEUMBIGA1UEChMLZU11ZGhyYSBJbmMx
-IDAeBgNVBAMTF2VtU2lnbiBFQ0MgUm9vdCBDQSAtIEMzMB4XDTE4MDIxODE4MzAw
-MFoXDTQzMDIxODE4MzAwMFowWjELMAkGA1UEBhMCVVMxEzARBgNVBAsTCmVtU2ln
-biBQS0kxFDASBgNVBAoTC2VNdWRocmEgSW5jMSAwHgYDVQQDExdlbVNpZ24gRUND
-IFJvb3QgQ0EgLSBDMzB2MBAGByqGSM49AgEGBSuBBAAiA2IABP2lYa57JhAd6bci
-MK4G9IGzsUJxlTm801Ljr6/58pc1kjZGDoeVjbk5Wum739D+yAdBPLtVb4Ojavti
-sIGJAnB9SMVK4+kiVCJNk7tCDK93nCOmfddhEc5lx/h//vXyqaNCMEAwHQYDVR0O
-BBYEFPtaSNCAIEDyqOkAB2kZd6fmw/TPMA4GA1UdDwEB/wQEAwIBBjAPBgNVHRMB
-Af8EBTADAQH/MAoGCCqGSM49BAMDA2gAMGUCMQC02C8Cif22TGK6Q04ThHK1rt0c
-3ta13FaPWEBaLd4gTCKDypOofu4SQMfWh0/434UCMBwUZOR8loMRnLDRWmFLpg9J
-0wD8ofzkpf9/rdcw0Md3f76BB1UwUCAU9Vc4CqgxUQ==
------END CERTIFICATE-----

salt/ca/files/blocklist/emsign-ecc-root-ca-g3.pem

@@ -1,15 +0,0 @@
------BEGIN CERTIFICATE-----
-MIICTjCCAdOgAwIBAgIKPPYHqWhwDtqLhDAKBggqhkjOPQQDAzBrMQswCQYDVQQG
-EwJJTjETMBEGA1UECxMKZW1TaWduIFBLSTElMCMGA1UEChMcZU11ZGhyYSBUZWNo
-bm9sb2dpZXMgTGltaXRlZDEgMB4GA1UEAxMXZW1TaWduIEVDQyBSb290IENBIC0g
-RzMwHhcNMTgwMjE4MTgzMDAwWhcNNDMwMjE4MTgzMDAwWjBrMQswCQYDVQQGEwJJ
-TjETMBEGA1UECxMKZW1TaWduIFBLSTElMCMGA1UEChMcZU11ZGhyYSBUZWNobm9s
-b2dpZXMgTGltaXRlZDEgMB4GA1UEAxMXZW1TaWduIEVDQyBSb290IENBIC0gRzMw
-djAQBgcqhkjOPQIBBgUrgQQAIgNiAAQjpQy4LRL1KPOxst3iAhKAnjlfSU2fySU0
-WXTsuwYc58Byr+iuL+FBVIcUqEqy6HyC5ltqtdyzdc6LBtCGI79G1Y4PPwT01xyS
-fvalY8L1X44uT6EYGQIrMgqCZH0Wk9GjQjBAMB0GA1UdDgQWBBR8XQKEE9TMipuB
-zhccLikenEhjQjAOBgNVHQ8BAf8EBAMCAQYwDwYDVR0TAQH/BAUwAwEB/zAKBggq
-hkjOPQQDAwNpADBmAjEAvvNhzwIQHWSVB7gYboiFBS+DCBeQyh+KTOgNG3qxrdWB
-CUfvO6wIBHxcmbHtRwfSAjEAnbpV/KlK6O3t5nYBQnvI+GDZjVGLVTv7jHvrZQnD
-+JbNR6iC8hZVdyR+EhCVBCyj
------END CERTIFICATE-----

salt/ca/files/blocklist/emsign-root-ca-c1.pem

@@ -1,21 +0,0 @@
------BEGIN CERTIFICATE-----
-MIIDczCCAlugAwIBAgILAK7PALrEzzL4Q7IwDQYJKoZIhvcNAQELBQAwVjELMAkG
-A1UEBhMCVVMxEzARBgNVBAsTCmVtU2lnbiBQS0kxFDASBgNVBAoTC2VNdWRocmEg
-SW5jMRwwGgYDVQQDExNlbVNpZ24gUm9vdCBDQSAtIEMxMB4XDTE4MDIxODE4MzAw
-MFoXDTQzMDIxODE4MzAwMFowVjELMAkGA1UEBhMCVVMxEzARBgNVBAsTCmVtU2ln
-biBQS0kxFDASBgNVBAoTC2VNdWRocmEgSW5jMRwwGgYDVQQDExNlbVNpZ24gUm9v
-dCBDQSAtIEMxMIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAz+upufGZ
-BczYKCFK83M0UYRWEPWgTywS4/oTmifQz/l5GnRfHXk5/Fv4cI7gklL35CX5VIPZ
-HdPIWoU/Xse2B+4+wM6ar6xWQio5JXDWv7V7Nq2s9nPczdcdioOl+yuQFTdrHCZH
-3DspVpNqs8FqOp099cGXOFgFixwR4+S0uF2FHYP+eF8LRWgYSKVGczQ7/g/IdrvH
-GPMF0Ybzhe3nudkyrVWIzqa2kbBPrH4VI5b2P/AgNBbeCsbEBEV5f6f9vtKppa+c
-xSMq9zwhbL2vj07FOrLzNBL834AaSaTUqZX3noleoomslMuoaJuvimUnzYnu3Yy1
-aylwQ6BpC+S5DwIDAQABo0IwQDAdBgNVHQ4EFgQU/qHgcB4qAzlSWkK+XJGFehiq
-TbUwDgYDVR0PAQH/BAQDAgEGMA8GA1UdEwEB/wQFMAMBAf8wDQYJKoZIhvcNAQEL
-BQADggEBAMJKVvoVIXsoounlHfv4LcQ5lkFMOycsxGwYFYDGrK9HWS8mC+M2sO87
-/kOXSTKZEhVb3xEp/6tT+LvBeA+snFOvV71ojD1pM/CjoCNjO2RnIkSt1XHLVip4
-kqNPEjE2NuLe/gDEo2APJ62gsIq1NnpSob0n9CAnYuhNlCQT5AoE6TyrLshDCUrG
-YQTlSTR+08TI9Q/Aqum6VF7zYytPT1DU/rl7mYw9wC68AivTxEDkigcxHpvOJpkT
-+xHqmiIMERnHXhuBUDDIlhJu58tBf5E7oke3VIAb3ADMmpDqw8NQBmIMMMAVSKeo
-WXzhriKi4gp6D/piq1JM4fHfyr6DDUI=
------END CERTIFICATE-----

salt/ca/files/blocklist/emsign-root-ca-c2.pem

@@ -1,32 +0,0 @@
------BEGIN CERTIFICATE-----
-MIIFcjCCA1qgAwIBAgIKLwq3aw3LSq8nWDANBgkqhkiG9w0BAQwFADBWMQswCQYD
-VQQGEwJVUzETMBEGA1UECxMKZW1TaWduIFBLSTEUMBIGA1UEChMLZU11ZGhyYSBJ
-bmMxHDAaBgNVBAMTE2VtU2lnbiBSb290IENBIC0gQzIwHhcNMTgwMjE4MTgzMDAw
-WhcNNDMwMjE4MTgzMDAwWjBWMQswCQYDVQQGEwJVUzETMBEGA1UECxMKZW1TaWdu
-IFBLSTEUMBIGA1UEChMLZU11ZGhyYSBJbmMxHDAaBgNVBAMTE2VtU2lnbiBSb290
-IENBIC0gQzIwggIiMA0GCSqGSIb3DQEBAQUAA4ICDwAwggIKAoICAQCMfX1lA+Tb
-mh9YInmRgOW97IVx4LUJf2DRZfs837Jrml+py64aVnYgWO4t6C78fgjfS7jX+c4T
-inIzEquWcI+zi0fd4Sc8NDf7JONp27VWX0qwUYqzLDRCt+s7zpLcfx1ky0zVIJj6
-L06uPyK3kIr9+YAsrVj+39utm6e2MBQsRNstSI3fCQYAGvoQTQ8fULauTqNWaYAk
-NYFe6HUHHQPp2u1Ua00odMXiD5oRFxLcDnGAcE1I/9E9mLCdkggXijYUmico7+Xw
-ZeFoPhva6eIJ5p03Lt3Du5W3EcHR0cJmmY1pyeA36JaXKWRNM9IRjYMVNCcp4jhB
-2tIYiZ+LVk8bwQ9/1c23txmv3u97taZlV22NF4ttS1qq3J+MOp0oGULBzpKfRx0q
-GVqbPukQNGAjOLIN8KDNQNzbR1iAl2d8H+MSoicBo4Aid8TjLWcNv48oCWL53ZrF
-BMTDjaIA6frG1t4IpbnHadA7qCJJe2qpJN6n2eQKAUn6UiQDHPsSqNBlcUhQ4Y/0
-Y0mU5rghm2OB9rXQS1Fb1JRCfJMNnJIm5AUB2+2RWzq5Tgz7SbSho8NsZk0UbQnF
-xciqQ9uoVTAsK14Sk9oG8Q3zfsM08cdPoRb0WlIZklR6mKD7L8nH/zfGu8PIJv94
-GGB9RZ9U4A69r3ePmy8MvrzfNxHKtH6svwIDAQABo0IwQDAdBgNVHQ4EFgQUs/eK
-pNYPiABZ6FEXT9V+7IYigZ0wDgYDVR0PAQH/BAQDAgEGMA8GA1UdEwEB/wQFMAMB
-Af8wDQYJKoZIhvcNAQEMBQADggIBADQlpiWM0cv2nZ0H5jVsBq0x2q62Q0LwqATs
-CFvyub7gxNCytRuoA8stmPOEu/lg8Igxj4FIjoyhIrWUVxyiLU7No4P+WjEUOwUT
-xIpkEOtvGUQ9fiOlcGHtIZDNBlZq7WpktXAxeV55RPPsor26p2FNAMRFfZQh0sLX
-hKgk8iulSSggqx8ezgPye63FaiYEi4c/dzRj3HOCnsZiwZZU02df5YpNFjxSwZvE
-41cjGpsrpWMfQFI2s53RbeXp47lSAxYE4NzjBFMe+EwFuEveBCJBEAH5rvYu3pi2
-orsJ424TqWEQV1tCsCkQz+Yq/Okal7yHAkKDeOXcP7oN4A+TdXc2pdqxuVCnBO0R
-mWz2JpGSSeJjiTk/OPwRsPNWtwG/KXL04o2ta3jiPpJuICVtWDAc9R3auBEgJl5r
-ShRmBdszG0LmzsHuZPCFSYC15RBDCOBsa8bDRJ8pBFU2Wi/CVXCACEuavgoveA4F
-a5bt38o0PWxsBP+MpocCdVtDMqzQhxy9IohKuXWAGresoIvKDg3xFk6rBOrjfVwJ
-elwi/xAisojHPJVQv9W1zVIoHp+EQg/4MQC21NbIX2RoioB+V3hK439b/w7deU8x
-2M8cl1OG0nPfbnARl5GPM7vJgi470jto4SeMg6HMAW3Egb56tQcNLwI9U8mZnNvR
-gUMrkAgL
------END CERTIFICATE-----

salt/ca/files/blocklist/emsign-root-ca-g1.pem

@@ -1,22 +0,0 @@
------BEGIN CERTIFICATE-----
-MIIDlDCCAnygAwIBAgIKMfXkYgxsWO3W2DANBgkqhkiG9w0BAQsFADBnMQswCQYD
-VQQGEwJJTjETMBEGA1UECxMKZW1TaWduIFBLSTElMCMGA1UEChMcZU11ZGhyYSBU
-ZWNobm9sb2dpZXMgTGltaXRlZDEcMBoGA1UEAxMTZW1TaWduIFJvb3QgQ0EgLSBH
-MTAeFw0xODAyMTgxODMwMDBaFw00MzAyMTgxODMwMDBaMGcxCzAJBgNVBAYTAklO
-MRMwEQYDVQQLEwplbVNpZ24gUEtJMSUwIwYDVQQKExxlTXVkaHJhIFRlY2hub2xv
-Z2llcyBMaW1pdGVkMRwwGgYDVQQDExNlbVNpZ24gUm9vdCBDQSAtIEcxMIIBIjAN
-BgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAk0u76WaK7p1b1TST0Bsew+eeuGQz
-f2N4aLTNLnF115sgxk0pvLZoYIr3IZpWNVrzdr3YzZr/k1ZLpVkGoZM0Kd0WNHVO
-8oG0x5ZOrRkVUkr+PHB1cM2vK6sVmjM8qrOLqs1D/fXqcP/tzxE7lM5OMhbTI0Aq
-d7OvPAEsbO2ZLIvZTmmYsvePQbAyeGHWDV/D+qJAkh1cF+ZwPjXnorfCYuKrpDhM
-tTk1b+oDafo6VGiFbdbyL0NVHpENDtjVaqSW0RM8LHhQ6DqS0hdW5TUaQBw+jSzt
-Od9C4INBdN+jzcKGYEho42kLVACL5HZpIQ15TjQIXhTCzLG3rdd8cIrHhQIDAQAB
-o0IwQDAdBgNVHQ4EFgQU++8Nhp6w492pufEhF38+/PB3KxowDgYDVR0PAQH/BAQD
-AgEGMA8GA1UdEwEB/wQFMAMBAf8wDQYJKoZIhvcNAQELBQADggEBAFn/8oz1h31x
-PaOfG1vR2vjTnGs2vZupYeveFix0PZ7mddrXuqe8QhfnPZHr5X3dPpzxz5KsbEjM
-wiI/aTvFthUvozXGaCocV685743QNcMYDHsAVhzNixl03r4PEuDQqqE/AjSxcM6d
-GNYIAwlG7mDgfrbESQRRfXBgvKqy/3lyeqYdPV8q+Mri/Tm3R7nrft8EI6/6nAYH
-6ftjk4BAtcZsCjEozgyfz7MjNYBBjWzEN3uBL4ChQEKF6dk4jeihU80Bv2noWgby
-RQuQ+q7hv53yrlc8pa6yVvSLZUDp/TGBLPQ5Cdjua6e0ph0VpZj3AYHYhX3zUVxx
-iN66zB+Afko=
------END CERTIFICATE-----

salt/ca/files/blocklist/emsign-root-ca-g2.pem

@@ -1,32 +0,0 @@
------BEGIN CERTIFICATE-----
-MIIFlTCCA32gAwIBAgILAIZNvw/jXtd9jtgwDQYJKoZIhvcNAQEMBQAwZzELMAkG
-A1UEBhMCSU4xEzARBgNVBAsTCmVtU2lnbiBQS0kxJTAjBgNVBAoTHGVNdWRocmEg
-VGVjaG5vbG9naWVzIExpbWl0ZWQxHDAaBgNVBAMTE2VtU2lnbiBSb290IENBIC0g
-RzIwHhcNMTgwMjE4MTgzMDAwWhcNNDMwMjE4MTgzMDAwWjBnMQswCQYDVQQGEwJJ
-TjETMBEGA1UECxMKZW1TaWduIFBLSTElMCMGA1UEChMcZU11ZGhyYSBUZWNobm9s
-b2dpZXMgTGltaXRlZDEcMBoGA1UEAxMTZW1TaWduIFJvb3QgQ0EgLSBHMjCCAiIw
-DQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAMNwGIWW2kHfHK+sXTNwxF07K+IV
-ySTuyFM2r1v002wUfcdT+zs5OM5QbMYFFnedXQI6gCFLsjKrcaej48Zt37OyEb3i
-aPs7CsP4kAyTwzKH9aZe6gXYHrJq40/ZVMNcQVI2PcIp40B/SAN2gUZ+ZaUtIOvV
-jEx26/ebNaXRIsthlkOG/caB+QRwDw1tl7338Zlv0M2oTBUy4B3e7dGP5pgXH71M
-jqHPCoNo+xv9f0NTBT+hUDa8h8wUtcGQq9CDeJTpjWcD2bP2AMdVG6oVpMAUeUzo
-cCyglvtFdUMjggxBbw4qhau1HXPG8Ot9hwL7ZMi8tkTzrvUIxxb8G9LF/7kKeCE7
-tGZaVzDTnXuifl3msR4ErHsQ4P7lVu2AIjIAhrAXoedDidb7pMcf7TABdrYUT1Jo
-G/AiK+J9jO6GTjeADD4LMDSBZhHMuBK/PJ/g0kGBt+/C1L+/HURzQhJkMlRnM6Rv
-XoCtfKopSlns5trZmTi971Wjbn88QXP61lGpBCUPwCjs7rpOYvSUJtI+lcbF+37q
-kIqOXYkVT3cupDSpw+H89kFtj5GKY+Xny4LxY+3IvDIRiyd6ky1DPj713DI0yqve
-EpsIr3A0PdwuyUI7CS1jg0NnGFT6Xxyr0xB+VDt83FJYW8v16k2pbaQ4kVxA3aXd
-X9dZYyVR1S59KM75AgMBAAGjQjBAMB0GA1UdDgQWBBTt7E1FYRgo57MjKBEcTaUn
-DV7s9DAOBgNVHQ8BAf8EBAMCAQYwDwYDVR0TAQH/BAUwAwEB/zANBgkqhkiG9w0B
-AQwFAAOCAgEACFC/ilQg8KTCVBxFJW/sazomkS0kNYbEIZg4B3obqwsJ7SX98z8Z
-gfzBpz0nYClwwJjWbFN1R2zY8pCEot6/dgmA8Vbq0GxhwPM5YN/SZquNyRIxO3cU
-dlAcwf+vSezdVCf9wOzvSAF3q0a5ljvbdbNJNpfScQVp7UUd5sBsZk8jXO1KQ/go
-/Vf/GDPnrIFmxpAIGE3sgnO8lAv9FzUaAeuv7HWe47xN9J7+bQzF93yHuIXACPTL
-pQHhg2zMv5C7BAbuDHfbj1Cu294Z832yhSfBcziWGskOvl3es2EcHytbS9c9P+0z
-Mpka7zGC1FHrvLb/FoduH86TeZt0QjZ6pcplNzoaxDnDvzTJ6CC2Eny+qH/APFCu
-VUv5/wjwF+HPm8Pup2ARj9cEp92+0qcerfHacNq5hMeGZdbA/dzdUR/5z5zXdxAk
-nl8mcfGb0eMNSTXQmmB/i4AecNnr72uYjzlaXUGYN7Nrb6XouG0pnh0/BBtWWp0U
-ShIPpWEAqs7RJBj6+1ZUYXZ4ObrCw962DxhN2p19Hxw9LtuUUcLqqTPrFXYvwO4t
-ouj7KJnAkaTUfXGdEaFVtFig1EA30WzJY2X1vAQ7hVnniCjgaXAGqjsU6sklNM9n
-xDx5rFCCCEtj9Kh8UHjGK2QqgP5kwgttjOApQMaCoezMfK4KD7WpOXU=
------END CERTIFICATE-----

salt/ca/files/blocklist/emsign-root-cs-ca-g2.pem

@@ -1,32 +0,0 @@
------BEGIN CERTIFICATE-----
-MIIFdjCCA16gAwIBAgIQCIYhdXKnxAzDuy7l1y1ubDANBgkqhkiG9w0BAQwFADBV
-MQswCQYDVQQGEwJJTjElMCMGA1UECgwcZU11ZGhyYSBUZWNobm9sb2dpZXMgTGlt
-aXRlZDEfMB0GA1UEAwwWZW1TaWduIFJvb3QgQ1MgQ0EgLSBHMjAeFw0yNDAyMDgw
-ODE1MzlaFw00OTAyMDcwODE1MzlaMFUxCzAJBgNVBAYTAklOMSUwIwYDVQQKDBxl
-TXVkaHJhIFRlY2hub2xvZ2llcyBMaW1pdGVkMR8wHQYDVQQDDBZlbVNpZ24gUm9v
-dCBDUyBDQSAtIEcyMIICIjANBgkqhkiG9w0BAQEFAAOCAg8AMIICCgKCAgEA4CVO
-xuBjdLJXpkrjosA+7ygTGaYzufUJrhQOeIZEuCqeCPI8hDqIu+MIqEqOlgDFetVM
-3Cor3CGBlGJzfzzlI31vyElvQq88jjCfo12Ghqcf+NAZDFduJk5+NgC0z3lfdiB6
-NNzxbfVkA+X6oDNNRioVUZsVFuIzT9Qt0Sh4KwQPRFBc/wI2yGpDuKHNsLehcECx
-Uw00m33xGYh9UkeL3reOmAaLYWZiO+Pd2vxPtrkXI4wyN4BMlESJ73uP0tyX9lq4
-M4yN2yh3i+ETI8/jzPjxHD7QFaVkCoS+uj2YmBa3mytlqlBgyOoKueNeotX8hfzB
-FNm962abpV4mN0SoC6hjkYv8IayseRPFv9VI0meQXg9OLRoNvBOqG5kw937FH0Li
-q3CIzKyvdyeYRT0LJdWA2iuB9l+4zzIfCwGyT4M4VDmJuPBhrTmjXKae6AUtm1eO
-q2f8gftA6J6AlbD0gRd/t8CrFssFNm+LYAEd36kWRBuolbaOfbSbEww84xNAgj4U
-SPwYjtNDsCkQjtgSOaDtDOmolN+Mbk528Y+LHMlbd4T3Xmp+VIWp5+70GhBDOA91
-hhtims+hHkXjRI2U7WrJLcTlcF8ykiymRbFKhwOBvTmtZNbHmDI7scU4wWUAsmW6
-tWaeeoM50KBl8ai28A6yBGYMO//03Ubvqiqst80CAwEAAaNCMEAwHQYDVR0OBBYE
-FOYcxqontIvyvYVkX6/0unKm0AF1MA4GA1UdDwEB/wQEAwIBBjAPBgNVHRMBAf8E
-BTADAQH/MA0GCSqGSIb3DQEBDAUAA4ICAQCv5Asord7fdQMT30emwb+oLuDUxdmJ
-DQHnzxIXoNvymDTbNHF9LqjeXc+X+XcjIV8PTp4o2I9wyVppHmcaVgRjN/G9FxeN
-5tCQ97v5sdx4eAdPljK1xqg7Vhfmzcp+7rSjJG7Sn9gMlZx81kL3Oa2qZj+W5Fi6
-tN4vaR9OLEyvKKHDG/eFxS/qghD1d/Clkb7UGGjBcWJlaZTWVALMKG+QCxiMoELi
-oeKaoBbZoXooxfF0mWdkIl9RWNU4r9O/yt66LBE9rj49dX19L+rGg71/4bTi5ua+
-+Wz60XaOc2CdHJaBSols5hWEx/LBjS7UzfU3uJfnpQXVDi0US5sFzIHIlS6kjh7h
-YuF4+/9ZAl4Bx3w2TNN7pVm7I39pgYl7XN6KZRwfkAv4aRswPqhWbQfr3+qfcC93
-cgTyFy2RG5YE/OfmpSs6VtYKawqsdEODz/p2nhZfSDrVDnEPvERqahttY5+gaWNc
-2fbibgKMfuejTZaJ3yttPslVSko5SDs0xKU423swu34sb/fdISqtOu4NzPCZiHSG
-ladaoITmSA6UWFk4fdqaLBI+xSxY5Et3S1APp5r3j/l1KrWPNbb1/+ydHN+YLbh8
-hCBIecKdk6VbnnFRlulm0d2RSgpfCRrWLomN8JHCxCMVv/hBQXz3AXGM1ZlfYTyl
-E1BpDby0G2eEkw==
------END CERTIFICATE-----

salt/ca/init.sls

@@ -10,4 +10,3 @@ include:
   - ca.server
 {% endif %}
   - ca.trustca
-  - ca.trust

salt/ca/trust.map.jinja

@@ -1,12 +0,0 @@
-# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at 
-# https://securityonion.net/license; you may not use this file except in compliance with the
-# Elastic License 2.0.
-
-{# Containers mount the extracted directory rather than single files: update-ca-trust replaces
-   files by rename, so a file bind mount would keep pointing at the old inode. #}
-{% set CATRUST = {
-    'dir': '/etc/pki/ca-trust/extracted:/etc/pki/ca-trust/extracted:ro',
-    'java': '/etc/pki/ca-trust/extracted/java/cacerts',
-    'pem': '/etc/pki/ca-trust/extracted/pem/tls-ca-bundle.pem'
-} %}

salt/ca/trust.sls

@@ -1,37 +0,0 @@
-# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at 
-# https://securityonion.net/license; you may not use this file except in compliance with the
-# Elastic License 2.0.
-
-ca_trust_anchor:
-  file.managed:
-    - name: /etc/pki/ca-trust/source/anchors/so-intca.crt
-    - source: salt://ca/files/ca.crt
-    - show_changes: False
-    - makedirs: True
-
-ca_trust_legacy_anchor:
-  file.absent:
-    - name: /etc/pki/ca-trust/source/anchors/ca.crt
-
-ca_trust_legacy_bundles:
-  file.absent:
-    - name: /opt/so/conf/ca
-
-# clean removes blocklist entries that are no longer shipped
-ca_trust_blocklist:
-  file.recurse:
-    - name: /etc/pki/ca-trust/source/blocklist
-    - source: salt://ca/files/blocklist
-    - clean: True
-    - makedirs: True
-    - file_mode: '0644'
-    - dir_mode: '0755'
-
-ca_trust_extract:
-  cmd.run:
-    - name: update-ca-trust extract
-    - onchanges:
-      - file: ca_trust_anchor
-      - file: ca_trust_legacy_anchor
-      - file: ca_trust_blocklist

salt/common/init.sls

@@ -117,25 +117,14 @@ elastic_curl_config:
 {% endif %}
 
 
-# A non-root owner here can chmod the directory and replace any script in it, including
-# the root-owned ones. 555 is the mode the filesystem RPM ships; root ignores it anyway.
-usr_sbin_perms:
-  file.directory:
-    - name: /usr/sbin
-    - user: root
-    - group: root
-    - mode: 555
-
 common_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939
     - file_mode: 755
     - show_changes: False
-    - require:
-      - file: usr_sbin_perms
 {% if GLOBALS.role == 'so-heavynode' %}
     - exclude_pat:
       - so-pcap-import
@@ -170,8 +159,8 @@ common_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin_jinja
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939 
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -184,8 +173,6 @@ so-status_script:
   file.managed:
     - name: /usr/sbin/so-status
     - source: salt://common/tools/sbin/so-status
-    - user: root
-    - group: root
     - mode: 755
 
 {% if GLOBALS.is_sensor %}
@@ -217,11 +204,9 @@ sostatus_log:
     - replace: False
 
 # Install sostatus check cron. This is used to populate Grid.
-# telegraf reads status.log on the same minute boundary this runs, so write aside and rename
-# rather than truncating the file it is reading
 so-status_check_cron:
   cron.present:
-    - name: '/usr/sbin/so-status -j > /opt/so/log/sostatus/status.log.tmp 2>&1; mv -f /opt/so/log/sostatus/status.log.tmp /opt/so/log/sostatus/status.log'
+    - name: '/usr/sbin/so-status -j > /opt/so/log/sostatus/status.log 2>&1'
     - identifier: so-status_check_cron
     - user: root
     - minute: '*/1'

salt/common/soup_scripts.sls

@@ -18,61 +18,47 @@ copy_so-common_common_tools_sbin:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_so-image-common_common_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_soup_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_so-firewall_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_so-yaml_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_so-repo-sync_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_bootstrap-salt_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/salt/scripts/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
-    - user: root
-    - group: root
-    - mode: 644
+    - preserve: True
 
 # This section is used to put the new script in place so that it can be called during soup.
 # It is faster than calling the states that normally manage them to put them in place.
@@ -81,60 +67,46 @@ copy_so-common_sbin:
     - name: /usr/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_so-image-common_sbin:
   file.copy:
     - name: /usr/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_soup_sbin:
   file.copy:
     - name: /usr/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_so-firewall_sbin:
   file.copy:
     - name: /usr/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_so-yaml_sbin:
   file.copy:
     - name: /usr/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_so-repo-sync_sbin:
   file.copy:
     - name: /usr/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True
 
 copy_bootstrap-salt_sbin:
   file.copy:
     - name: /usr/sbin/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
     - force: True
-    - user: root
-    - group: root
-    - mode: 755
+    - preserve: True

salt/common/tools/sbin/so-common

@@ -240,8 +240,7 @@ copy_new_files() {
   cd $UPDATE_DIR
   rsync -a salt $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
   rsync -a pillar $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
-  # Root-executed code; SOC only needs to read it. Local dirs stay socore-owned.
-  chown -R root:root $DEFAULT_SALT_DIR/
+  chown -R socore:socore $DEFAULT_SALT_DIR/
   cd /tmp
 }
 

salt/common/tools/sbin/so-common-status-check

@@ -9,7 +9,6 @@ import sys
 import subprocess
 import os
 import json
-import tempfile
 
 sys.path.append('/opt/saltstack/salt/lib/python3.10/site-packages/')
 import salt.config
@@ -18,21 +17,6 @@ import salt.loader
 __opts__ = salt.config.minion_config('/etc/salt/minion')
 __grains__ = salt.loader.grains(__opts__)
 
-def write_atomic(path, value):
-  # telegraf reads these files on its own schedule; replacing them by rename means it never
-  # reads a truncated file and reports an empty value as if it were real
-  directory = os.path.dirname(path)
-  handle, temp = tempfile.mkstemp(dir=directory)
-  try:
-    with os.fdopen(handle, 'w') as f:
-      f.write(str(value))
-    os.chmod(temp, 0o644)
-    os.replace(temp, path)
-  except Exception:
-    os.path.exists(temp) and os.unlink(temp)
-    raise
-
-
 def check_needs_restarted():
   osfam = __grains__['os_family']
   val = '0'
@@ -50,7 +34,8 @@ def check_needs_restarted():
   else:
     fail("Unsupported OS")
 
-  write_atomic(outfile, val)
+  with open(outfile, 'w') as f:
+    f.write(val)
 
 def check_for_fps():
     feat = 'fps'
@@ -71,7 +56,8 @@ def check_for_fps():
           # Unknown, so assume 0
           fps = 0
 
-    write_atomic('/opt/so/log/sostatus/fps_enabled', fps)
+    with open('/opt/so/log/sostatus/fps_enabled', 'w') as f:
+       f.write(str(fps))
 
 def check_for_lks():
     feat = 'Lks'
@@ -94,7 +80,8 @@ def check_for_lks():
                                 lks = 1
         if lks:
             break
-    write_atomic('/opt/so/log/sostatus/lks_enabled', lks)
+    with open('/opt/so/log/sostatus/lks_enabled', 'w') as f:
+       f.write(str(lks))
 
 def fail(msg):
   print(msg, file=sys.stderr)

salt/common/tools/sbin/so-log-check

@@ -177,8 +177,6 @@ if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Unexpected authorization header" # expected WARN log lines indicating invalid auth header
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Missing ory_kratos_session cookie" # expected WARN log lines indicating invalid auth header
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Static assets preprocessor only supports GET and HEAD requests" # expected WARN log lines indicating invalid auth header
-    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|respondError"                 # respondError is a function name, output via http middleware as standard request logging
-    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|GET /kibana/"                 # Ignore Kibana queries with triggered words
 fi
 
 if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
@@ -242,7 +240,7 @@ if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|marked for removal"           # docker container getting recycled
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|tcp 127.0.0.1:6791: bind: address already in use" # so-elastic-fleet agent restarting. Seen starting w/ 8.18.8 https://github.com/elastic/kibana/issues/201459
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|TransformTask\] \[logs-.*user so_kibana lacks the required permissions" # Known issue with integrations starting transform jobs that are explicitly not allowed to start as a system user
-    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # so-dockerregistry logs a tag lookup miss during image copy; not tied to one docker version
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # appears in so-dockerregistry log for so-tcpreplay following docker upgrade to 29.2.1-1
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Could not index event to Elasticsearch.*\"version\" => \"9.0.8\"" # Expected during Elastic upgrade temporarily, as policies referencing older pipelines are updated
 fi
 

salt/common/tools/sbin/so-sensor-clean

@@ -8,37 +8,21 @@
 # Elastic License 2.0.
 
 
-SENSOR_DIR="${SENSOR_DIR:-/nsm}"
+SENSOR_DIR='/nsm'
 CRIT_DISK_USAGE=90
-LOG="${LOG:-/opt/so/log/sensor_clean.log}"
-LOCK="${LOCK:-/var/tmp/so-sensor-clean.lock}"
-MAX_PASSES=100
+CUR_USAGE=$(df -P $SENSOR_DIR | tail -1 | awk '{print $5}' | tr -d %)
+LOG="/opt/so/log/sensor_clean.log"
+TODAY=$(date -u "+%Y-%m-%d")
 
-ZEEK_LOGS="$SENSOR_DIR/zeek/logs"
-STRELKA_FILES="$SENSOR_DIR/strelka/processed"
-SURICATA_LOGS="$SENSOR_DIR/suricata"
-PCAPS="$SENSOR_DIR/pcapout"
-
-log() {
-	echo "$(date) - $*" >>"$LOG"
-}
-
-disk_usage() {
-	df -P "$SENSOR_DIR" | tail -1 | awk '{print $5}' | tr -d %
-}
-
-disk_avail() {
-	df -P "$SENSOR_DIR" | tail -1 | awk '{print $4}'
-}
-
-# sets REMOVED=1 if anything was actually deleted
 clean() {
 	## find the oldest Zeek logs directory
-	OLDEST_DIR=$(ls "$ZEEK_LOGS" 2>/dev/null | grep -v "current" | grep -v "stats" | grep -v "packetloss" | grep -v "zeek_clean" | sort | head -n 1)
-	if [ -n "$OLDEST_DIR" ]; then
-		log "Removing directory: $ZEEK_LOGS/$OLDEST_DIR"
-		rm -rf "$ZEEK_LOGS/$OLDEST_DIR"
-		REMOVED=1
+	OLDEST_DIR=$(ls /nsm/zeek/logs/ | grep -v "current" | grep -v "stats" | grep -v "packetloss" | grep -v "zeek_clean" | sort | head -n 1)
+	if [ -z "$OLDEST_DIR" -o "$OLDEST_DIR" == ".." -o "$OLDEST_DIR" == "." ]; then
+		echo "$(date) - No old Zeek logs available to clean up in /nsm/zeek/logs/" >>$LOG
+		#exit 0
+	else
+		echo "$(date) - Removing directory: /nsm/zeek/logs/$OLDEST_DIR" >>$LOG
+		rm -rf /nsm/zeek/logs/"$OLDEST_DIR"
 	fi
 
 	## Remarking for now, as we are moving extracted files to /nsm/strelka/processed
@@ -59,73 +43,58 @@ clean() {
 	#fi
 
 	## Clean up Zeek extracted files processed by Strelka
-	OLDEST_STRELKA=$(find "$STRELKA_FILES" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
-	if [ -n "$OLDEST_STRELKA" ]; then
+	STRELKA_FILES='/nsm/strelka/processed'
+	OLDEST_STRELKA=$(find $STRELKA_FILES -type f -printf '%T+ %p\n' | sort -n | head -n 1)
+	if [ -z "$OLDEST_STRELKA" -o "$OLDEST_STRELKA" == ".." -o "$OLDEST_STRELKA" == "." ]; then
+		echo "$(date) - No old files available to clean up in $STRELKA_FILES" >>$LOG
+	else
 		OLDEST_STRELKA_DATE=$(echo $OLDEST_STRELKA | awk '{print $1}' | cut -d+ -f1)
-		log "Removing extracted files for $OLDEST_STRELKA_DATE"
-		REMOVED=1
-		find "$STRELKA_FILES" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_STRELKA_DATE | awk '{print $2}' | while read FILE; do
-			log "Removing file: $FILE"
+		OLDEST_STRELKA_FILE=$(echo $OLDEST_STRELKA | awk '{print $2}')
+		echo "$(date) - Removing extracted files for $OLDEST_STRELKA_DATE" >>$LOG
+		find $STRELKA_FILES -type f -printf '%T+ %p\n' | grep $OLDEST_STRELKA_DATE | awk '{print $2}' | while read FILE; do
+			echo "$(date) - Removing file: $FILE" >>$LOG
 			rm -f "$FILE"
 		done
 	fi
 
 	## Clean up Suricata log files
-	OLDEST_SURICATA=$(find "$SURICATA_LOGS" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
-	if [ -n "$OLDEST_SURICATA" ]; then
+	SURICATA_LOGS='/nsm/suricata'
+	OLDEST_SURICATA=$(find $SURICATA_LOGS -type f -printf '%T+ %p\n' | sort -n | head -n 1)
+	if [[ -z "$OLDEST_SURICATA" ]] || [[ "$OLDEST_SURICATA" == ".." ]] || [[ "$OLDEST_SURICATA" == "." ]]; then
+		echo "$(date) - No old files available to clean up in $SURICATA_LOGS" >>$LOG
+	else
 		OLDEST_SURICATA_DATE=$(echo $OLDEST_SURICATA | awk '{print $1}' | cut -d+ -f1)
-		log "Removing logs for $OLDEST_SURICATA_DATE"
-		REMOVED=1
-		find "$SURICATA_LOGS" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_SURICATA_DATE | awk '{print $2}' | while read FILE; do
-			log "Removing file: $FILE"
+		OLDEST_SURICATA_FILE=$(echo $OLDEST_SURICATA | awk '{print $2}')
+		echo "$(date) - Removing logs for $OLDEST_SURICATA_DATE" >>$LOG
+		find $SURICATA_LOGS -type f -printf '%T+ %p\n' | grep $OLDEST_SURICATA_DATE | awk '{print $2}' | while read FILE; do
+			echo "$(date) - Removing file: $FILE" >>$LOG
 			rm -f "$FILE"
 		done
 	fi
 
 	## Clean up extracted pcaps
-	OLDEST_PCAP=$(find "$PCAPS" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
-	if [ -n "$OLDEST_PCAP" ]; then
+	PCAPS='/nsm/pcapout'
+	OLDEST_PCAP=$(find $PCAPS -type f -printf '%T+ %p\n' | sort -n | head -n 1)
+	if [ -z "$OLDEST_PCAP" -o "$OLDEST_PCAP" == ".." -o "$OLDEST_PCAP" == "." ]; then
+		echo "$(date) - No old files available to clean up in $PCAPS" >>$LOG
+	else
 		OLDEST_PCAP_DATE=$(echo $OLDEST_PCAP | awk '{print $1}' | cut -d+ -f1)
-		log "Removing extracted files for $OLDEST_PCAP_DATE"
-		REMOVED=1
-		find "$PCAPS" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_PCAP_DATE | awk '{print $2}' | while read FILE; do
-			log "Removing file: $FILE"
+		OLDEST_PCAP_FILE=$(echo $OLDEST_PCAP | awk '{print $2}')
+		echo "$(date) - Removing extracted files for $OLDEST_PCAP_DATE" >>$LOG
+		find $PCAPS -type f -printf '%T+ %p\n' | grep $OLDEST_PCAP_DATE | awk '{print $2}' | while read FILE; do
+			echo "$(date) - Removing file: $FILE" >>$LOG
 			rm -f "$FILE"
 		done
 	fi
 }
 
-# Only one instance at a time; the lock is the fd, so it releases on any exit
-exec 9>"$LOCK" || exit 1
-if ! flock -n 9; then
-	log "another so-sensor-clean is already running (lock $LOCK held); exiting"
-	exit 0
+# Check to see if we are already running
+NUM_RUNNING=$(pgrep -cf "/bin/bash /usr/sbin/so-sensor-clean")
+[ "$NUM_RUNNING" -gt 1 ] && echo "$(date) - $NUM_RUNNING sensor clean script processes running...exiting." >>$LOG && exit 0
+
+if [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; then
+	while [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; do
+		clean
+		CUR_USAGE=$(df -P $SENSOR_DIR | tail -1 | awk '{print $5}' | tr -d %)
+	done
 fi
-
-CUR_USAGE=$(disk_usage)
-[ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ] || exit 0
-
-log "$SENSOR_DIR at ${CUR_USAGE}% (threshold ${CRIT_DISK_USAGE}%); starting cleanup"
-
-PASS=0
-while [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; do
-	PASS=$((PASS + 1))
-	if [ "$PASS" -gt "$MAX_PASSES" ]; then
-		log "stopping after $MAX_PASSES passes; $SENSOR_DIR still at ${CUR_USAGE}%"
-		break
-	fi
-
-	REMOVED=0
-	BEFORE=$(disk_avail)
-	clean
-	CUR_USAGE=$(disk_usage)
-
-	if [ "$REMOVED" -eq 0 ]; then
-		log "nothing left to remove in $ZEEK_LOGS, $STRELKA_FILES, $SURICATA_LOGS, $PCAPS; $SENSOR_DIR still at ${CUR_USAGE}% - space is consumed outside of NSM cleanup scope"
-		break
-	fi
-	if [ "$(disk_avail)" -le "$BEFORE" ]; then
-		log "pass $PASS freed no space; $SENSOR_DIR still at ${CUR_USAGE}% - stopping until next run"
-		break
-	fi
-done

salt/common/tools/sbin_jinja/so-raid-status

@@ -125,6 +125,4 @@ else
   RAIDSTATUS=1
 fi
 
-# telegraf reads this file; write aside and rename so it never sees a half-written file
-echo "nsmraid=$RAIDSTATUS" > /opt/so/log/raid/status.log.tmp
-mv -f /opt/so/log/raid/status.log.tmp /opt/so/log/raid/status.log
+echo "nsmraid=$RAIDSTATUS" > /opt/so/log/raid/status.log

salt/desktop/packages.sls

@@ -438,10 +438,6 @@ install_networkminer:
   pkg.latest:
     - name: securityonion-networkminer
 
-install_so_crates:
-  pkg.latest:
-    - name: securityonion-so-crates
-
 {% else %}
 
 desktop_packages_os_fail:

salt/desktop/trusted-ca.sls

@@ -1,10 +1,18 @@
-{% from 'vars/globals.map.jinja' import GLOBALS %}
+ {% from 'vars/globals.map.jinja' import GLOBALS %}
 
 {# we only want this state to run it is CentOS #}
 {% if GLOBALS.os == 'OEL' %}
 
-include:
-  - ca.trust
+trusted_ca:
+  file.managed:
+    - name: /etc/pki/ca-trust/source/anchors/ca.crt
+    - source: salt://ca/files/ca.crt
+
+update_ca_certs:
+  cmd.run:
+    - name: update-ca-trust
+    - onchanges:
+      - file: trusted_ca
 
 {% else %}
 

salt/docker/defaults.yaml

@@ -1,12 +1,6 @@
 docker:
   range: '172.17.1.0/24'
   gateway: '172.17.1.1'
-  networks:
-    sobridge: {}
-    soauth:
-      range: '172.17.2.0/24'
-      gateway: '172.17.2.1'
-      manager_only: True
   ulimits:
     - name: nofile
       soft: 1048576
@@ -64,18 +58,18 @@ docker:
       ulimits: []
     'so-kratos':
       final_octet: 28
-      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4433:4433
+        - 0.0.0.0:4434:4434
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
       ulimits: []
     'so-hydra':
       final_octet: 30
-      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4444:4444
+        - 0.0.0.0:4445:4445
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
@@ -134,7 +128,6 @@ docker:
       ulimits: []
     'so-soc':
       final_octet: 34
-      networks: ['sobridge', 'soauth']
       port_bindings:
         - 0.0.0.0:9822:9822
       custom_bind_mounts: []

salt/docker/docker.map.jinja

@@ -1,26 +1,8 @@
 {% import_yaml 'docker/defaults.yaml' as DOCKERDEFAULTS %}
 {% set DOCKERMERGED = salt['pillar.get']('docker', DOCKERDEFAULTS.docker, merge=True) %}
-
-{% if DOCKERMERGED.networks.sobridge is not mapping %}
-{%   do DOCKERMERGED.networks.update({'sobridge': {}}) %}
-{% endif %}
-{% do DOCKERMERGED.networks['sobridge'].update({'range': DOCKERMERGED.range, 'gateway': DOCKERMERGED.gateway}) %}
-
-{% for netname, net in DOCKERMERGED.networks.items() %}
-{%   set RANGESPLIT = net.range.split('.') %}
-{%   do net.update({'prefix': RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.'}) %}
-{% endfor %}
+{% set RANGESPLIT = DOCKERMERGED.range.split('.') %}
+{% set FIRSTTHREE = RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.' %}
 
 {% for container, vals in DOCKERMERGED.containers.items() %}
-{%   set CONTAINER_NETS = vals.get('networks', ['sobridge']) %}
-{%   set IPS = {} %}
-{%   for netname in CONTAINER_NETS %}
-{%     do IPS.update({netname: DOCKERMERGED.networks[netname].prefix ~ vals.final_octet}) %}
-{%   endfor %}
-{%   do DOCKERMERGED.containers[container].update({
-         'networks': CONTAINER_NETS,
-         'ips': IPS,
-         'network': CONTAINER_NETS[0],
-         'ip': IPS[CONTAINER_NETS[0]]
-       }) %}
+{%   do DOCKERMERGED.containers[container].update({'ip': FIRSTTHREE ~ DOCKERMERGED.containers[container].final_octet}) %}
 {% endfor %}

salt/docker/init.sls

@@ -18,10 +18,10 @@ dockergroup:
 dockerheldpackages:
   pkg.installed:
     - pkgs:
-      - containerd.io: 2.3.6-1.el9
-      - docker-ce: 3:29.8.1-1.el9
-      - docker-ce-cli: 1:29.8.1-1.el9
-      - docker-ce-rootless-extras: 29.8.1-1.el9
+      - containerd.io: 2.2.1-1.el9
+      - docker-ce: 3:29.2.1-1.el9
+      - docker-ce-cli: 1:29.2.1-1.el9
+      - docker-ce-rootless-extras: 29.2.1-1.el9
     - hold: True
     - update_holds: True
 
@@ -71,19 +71,15 @@ dockerreserveports:
     - source: salt://common/files/99-reserved-ports.conf
     - name: /etc/sysctl.d/99-reserved-ports.conf
 
-{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
-{% if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
-sos_docker_net_{{ NETNAME }}:
+sos_docker_net:
   docker_network.present:
-    - name: {{ NETNAME }}
-    - subnet: {{ NETWORK.range }}
-    - gateway: {{ NETWORK.gateway }}
+    - name: sobridge
+    - subnet: {{ DOCKERMERGED.range }}
+    - gateway: {{ DOCKERMERGED.gateway }}
     - options:
-        com.docker.network.bridge.name: '{{ NETNAME }}'
+        com.docker.network.bridge.name: 'sobridge'
         com.docker.network.driver.mtu: '1500'
         com.docker.network.bridge.enable_ip_masquerade: 'true'
         com.docker.network.bridge.enable_icc: 'true'
         com.docker.network.bridge.host_binding_ipv4: '0.0.0.0'
-    - unless: ip l | grep {{ NETNAME }}
-{% endif %}
-{% endfor %}
+    - unless: ip l | grep sobridge

salt/docker/soc_docker.yaml

@@ -7,40 +7,6 @@ docker:
     description: Default docker IP range for containers.
     helpLink: docker
     advanced: True
-  networks:
-    sobridge:
-      description: |
-        The default docker network, carrying most containers. Its range and gateway are taken
-        from the docker.range and docker.gateway settings above rather than set here.
-      helpLink: docker
-      readonly: True
-      advanced: True
-      global: True
-    soauth:
-      range:
-        description: |
-          IP range for the soauth docker network, an isolated network for the authentication
-          services, so that the Kratos and Hydra admin APIs are only reachable from the
-          containers placed on it.
-        helpLink: docker
-        readonly: True
-        advanced: True
-        global: True
-      gateway:
-        description: Gateway for the soauth docker network.
-        helpLink: docker
-        readonly: True
-        advanced: True
-        global: True
-      manager_only:
-        description: |
-          Limits the soauth network to grid members running the authentication containers,
-          instead of creating it on every node.
-        helpLink: docker
-        readonly: True
-        advanced: True
-        global: True
-        forcedType: bool
   ulimits:
     description: |
       Default ulimit settings applied to all containers via the Docker daemon. Each entry specifies a resource name (e.g. nofile, memlock, core, nproc) with soft and hard limits. Individual container ulimits override these defaults. Valid resource names include: cpu, fsize, data, stack, core, rss, nproc, nofile, memlock, as, locks, sigpending, msgqueue, nice, rtprio, rttime.
@@ -68,16 +34,6 @@ docker:
         readonly: True
         advanced: True
         global: True
-      networks:
-        description: |
-          Docker networks this container is attached to. The first entry is the container's
-          primary network and determines the address its published ports are forwarded to.
-          Defaults to sobridge when unset.
-        helpLink: docker
-        readonly: True
-        advanced: True
-        global: True
-        forcedType: "[]string"
       port_bindings:
         description: List of port bindings for the container.
         helpLink: docker

salt/elastalert/config.sls

@@ -21,7 +21,6 @@ elastalert:
     - gid: 933
     - home: /opt/so/conf/elastalert
     - createhome: False
-    - shell: /sbin/nologin
 
 elastalogdir:
   file.directory:
@@ -34,8 +33,8 @@ elastalert_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elastalert/tools/sbin
-    - user: root
-    - group: root
+    - user: 933
+    - group: 939
     - file_mode: 755
 
 #elastalert_sbin_jinja:

salt/elastalert/defaults.yaml

@@ -10,7 +10,7 @@ elastalert:
     buffer_time:
       minutes: 10
     old_query_limit:
-      minutes: 1440
+      minutes: 5
     es_port: 9200
     es_conn_timeout: 55
     max_query_size: 5000

salt/elastalert/enabled.sls

@@ -6,11 +6,9 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 
 include:
-  - ca.trust
   - elastalert.config
   - elastalert.sostatus
 
@@ -30,7 +28,6 @@ so-elastalert:
         - ipv4_address: {{ DOCKERMERGED.containers['so-elastalert'].ip }}
     - detach: True
     - binds:
-      - {{ CATRUST.dir }}
       - /opt/so/rules/elastalert:/opt/elastalert/rules/:ro
       - /opt/so/log/elastalert:/var/log/elastalert:rw
       - /opt/so/conf/elastalert/modules/:/opt/elastalert/modules/:ro
@@ -49,9 +46,8 @@ so-elastalert:
       - {{ XTRAHOST }}
         {% endfor %}
       {% endif %}
-    - environment:
-      - REQUESTS_CA_BUNDLE=/etc/pki/tls/certs/ca-bundle.crt
       {% if DOCKERMERGED.containers['so-elastalert'].extra_env %}
+    - environment:
         {% for XTRAENV in DOCKERMERGED.containers['so-elastalert'].extra_env %}
       - {{ XTRAENV }}
         {% endfor %}
@@ -69,7 +65,6 @@ so-elastalert:
       - file: elastacustmodulesdir
       - file: elastaconf
     - watch:
-      - cmd: ca_trust_extract
       - file: elastaconf
     - onlyif:
       - "so-elasticsearch-query / | jq -r '.version.number[0:1]' | grep -q 9" {# only run this state if elasticsearch is version 9 #}

salt/elastalert/files/modules/so/conftest.py

@@ -1,80 +0,0 @@
-# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
-# https://securityonion.net/license; you may not use this file except in compliance with the
-# Elastic License 2.0.
-
-from datetime import datetime
-import json
-import logging
-import sys
-import types
-
-# stand-ins when ElastAlert isn't installed (CI)
-try:
-    import elastalert.alerts  # noqa: F401
-except ImportError:
-
-    class Alerter:
-        def __init__(self, rule):
-            self.rule = rule
-
-    class DateTimeEncoder(json.JSONEncoder):
-        def default(self, obj):
-            return obj.isoformat() if hasattr(obj, 'isoformat') else json.JSONEncoder.default(self, obj)
-
-    class EAException(Exception):
-        pass
-
-    def lookup_es_key(doc, term):
-        for part in term.split('.'):
-            if not isinstance(doc, dict) or part not in doc:
-                return None
-            doc = doc[part]
-        return doc
-
-    def ts_to_dt(value):
-        return value if isinstance(value, datetime) else datetime.fromisoformat(value)
-
-    def elasticsearch_client(conf):
-        return None  # tests set the alerter's client
-
-    alerts = types.ModuleType('elastalert.alerts')
-    alerts.Alerter = Alerter
-    alerts.DateTimeEncoder = DateTimeEncoder
-    util = types.ModuleType('elastalert.util')
-    util.EAException = EAException
-    util.elastalert_logger = logging.getLogger('elastalert')
-    util.lookup_es_key = lookup_es_key
-    util.ts_to_dt = ts_to_dt
-    util.elasticsearch_client = elasticsearch_client
-    package = types.ModuleType('elastalert')
-    package.alerts = alerts
-    package.util = util
-    sys.modules.update({'elastalert': package, 'elastalert.alerts': alerts, 'elastalert.util': util})
-
-# stand-ins when elasticsearch-py isn't installed (CI)
-try:
-    import elasticsearch.exceptions  # noqa: F401
-except ImportError:
-
-    class ElasticsearchException(Exception):
-        pass
-
-    class TransportError(ElasticsearchException):
-        pass
-
-    class ConnectionError(TransportError):
-        pass
-
-    class ConflictError(TransportError):
-        pass
-
-    class RequestError(TransportError):
-        pass
-
-    exceptions = types.ModuleType('elasticsearch.exceptions')
-    for cls in (ElasticsearchException, TransportError, ConnectionError, ConflictError, RequestError):
-        setattr(exceptions, cls.__name__, cls)
-    es_package = types.ModuleType('elasticsearch')
-    es_package.exceptions = exceptions
-    sys.modules.update({'elasticsearch': es_package, 'elasticsearch.exceptions': exceptions})

salt/elastalert/files/modules/so/securityonion-es.py

@@ -1,269 +1,63 @@
 # -*- coding: utf-8 -*-
 
 # Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at 
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-from datetime import datetime, timezone
-import hashlib
-import ipaddress
-import json
-import re
-import uuid
+
+from time import gmtime, strftime
+import requests,json
+from elastalert.alerts import Alerter
 
 import urllib3
-from elasticsearch.exceptions import ConflictError, ElasticsearchException, RequestError
-from elastalert.alerts import Alerter, DateTimeEncoder
-from elastalert.util import EAException, elastalert_logger, elasticsearch_client, lookup_es_key, ts_to_dt
-
-# grid runs verify_certs: false; also quiets ElastAlert's own queries
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
-ALERT_INDEX = 'logs-detections.alerts-so'
-# ES error text kept in logs and alerts
-ERROR_TEXT_LIMIT = 500
-# a match missing backend columns (window_start, count, @timestamp); the alert is still written
-MATCH_ERRORS = (KeyError, TypeError, ValueError)
-
-
 class SecurityOnionESAlerter(Alerter):
     """
     Use matched data to create alerts in Elasticsearch.
     """
 
-    required_options = {'detection_title', 'sigma_level'}
-    optional_fields = ['sigma_category', 'sigma_product', 'sigma_service', 'sigma_correlation']
-
-    # count column and default summary per type; stored alert data, so not localized
-    CORRELATION_COUNTS = {
-        'event_count': ('event_count', '%count% events'),
-        'value_count': ('value_count', '%count% distinct values'),
-        'temporal': ('event_type_count', '%count% correlated rules matched'),
-        'value_sum': ('value_sum', 'total %count%'),
-        'value_avg': ('value_avg', 'average %count%'),
-        'value_percentile': ('value_percentile', 'percentile %count%'),
-        'value_median': ('value_median', 'median %count%'),
-    }
-    PLACEHOLDER = re.compile(r'%([^%\s]+)%')
-    # group-by fields copied into ECS related.*
-    RELATED_USERS = {'user.name', 'winlog.event_data.TargetUserName', 'winlog.event_data.SubjectUserName'}
-    RELATED_HOSTS = {'host.name', 'host.hostname', 'winlog.computer_name'}
-
-    def __init__(self, rule):
-        super().__init__(rule)
-        # uses the grid's TLS, auth and timeout settings
-        self.es = elasticsearch_client(rule)
-
-    @property
-    def is_correlation(self):
-        return bool(self.rule.get('sigma_correlation'))
-
-    def query_keys(self):
-        """compound_query_key holds the list; query_key is flattened to a string."""
-        if self.rule.get('compound_query_key'):
-            return self.rule['compound_query_key']
-        if self.rule.get('query_key'):
-            return [self.rule['query_key']]
-        return []
-
-    def alert_id(self, match):
-        """Stable id: window end + group values for correlations, source _id otherwise; random without one."""
-        if self.is_correlation:
-            # ungrouped rows have a hashed _id that changes with the count
-            values = ''.join(f"|{lookup_es_key(match, k)}" for k in self.query_keys())
-            key = f"{self.rule['detection_public_id']}|{ts_to_dt(match['@timestamp']).isoformat()}{values}"
-        elif match.get('_id'):
-            key = f"{self.rule['detection_public_id']}|{match['_id']}"
-        else:
-            return uuid.uuid4().hex
-
-        return hashlib.sha256(key.encode('utf-8')).hexdigest()
-
-    def group(self, match):
-        """Group-by values, joined like ElastAlert's realert key."""
-        return ', '.join(str(lookup_es_key(match, k)) for k in self.query_keys())
-
-    def related_bucket(self, key):
-        if key == 'ip' or key.endswith('.ip'):
-            return 'ip'
-        if key in self.RELATED_USERS or key.endswith('.user.name'):
-            return 'user'
-        if key in self.RELATED_HOSTS:
-            return 'hosts'
-        return None
-
-    @staticmethod
-    def valid_ip(value):
-        try:
-            ipaddress.ip_address(value)
-            return True
-        except ValueError:
-            return False
-
-    def related(self, match):
-        """ECS related.* from group-by values; skips invalid IPs."""
-        related = {}
-        for key in self.query_keys():
-            bucket = self.related_bucket(key)
-            if not bucket:
-                continue
-            # original spellings of a lowercased group
-            value = lookup_es_key(match, f"{key}_spellings")
-            if value is None:
-                value = lookup_es_key(match, key)
-            for v in value if isinstance(value, list) else [value]:
-                if v is None or (bucket == 'ip' and not self.valid_ip(str(v))):
-                    continue
-                # dict: ordered and deduped
-                related.setdefault(bucket, {})[str(v)] = None
-        return {bucket: list(values) for bucket, values in related.items()}
-
-    def event_data(self, match):
-        """The match minus the compound query_key field, which ES would map by its last part."""
-        if not self.rule.get('compound_query_key'):
-            return match
-        return {k: v for k, v in match.items() if k != self.rule['query_key']}
-
-    @staticmethod
-    def format_value(value):
-        if isinstance(value, list):
-            shown = ', '.join(str(v) for v in value[:3])
-            return shown if len(value) <= 3 else f"{shown} and {len(value) - 3} more"
-        return str(value)
-
-    @staticmethod
-    def format_count(value):
-        if isinstance(value, float) and not value.is_integer():
-            return f"{value:,.2f}"
-        if isinstance(value, (int, float)):
-            return f"{int(value):,}"
-        return str(value)
-
-    @staticmethod
-    def format_duration(seconds):
-        for unit, size in (('hour', 3600), ('minute', 60)):
-            if seconds >= 2 * size:
-                return f"{seconds // size} {unit}s"
-        return f"{seconds} second{'' if seconds == 1 else 's'}"
-
-    def summary(self, match):
-        """One-line correlation summary."""
-        column, label = self.CORRELATION_COUNTS.get(self.rule['sigma_correlation'], (None, '%count%'))
-        start = ts_to_dt(match['window_start'])
-        end = ts_to_dt(match['@timestamp'])
-        values = {
-            'count': self.format_count(match.get(column)),
-            'start': start.strftime('%Y-%m-%d %H:%M:%S UTC'),
-            'end': end.strftime('%Y-%m-%d %H:%M:%S UTC'),
-            'duration': self.format_duration(int((end - start).total_seconds())),
-        }
-
-        template = self.rule.get('summary_template')
-        if not template:
-            groups = ', '.join(f"{k} %{k}%" for k in self.query_keys())
-            template = f"{label} for {groups} in %duration%" if groups else f"{label} in %duration%"
-
-        def fill(m):
-            if m[1] in values:
-                return values[m[1]]
-            value = lookup_es_key(match, m[1])
-            # unknown placeholders stay visible so typos show
-            return m[0] if value is None else self.format_value(value)
-
-        return self.PLACEHOLDER.sub(fill, template)
+    required_options = set(['detection_title', 'sigma_level'])
+    optional_fields = ['sigma_category', 'sigma_product', 'sigma_service']
 
     def alert(self, matches):
         for match in matches:
-            try:
-                alert_id = self.alert_id(match)
-            except MATCH_ERRORS as e:
-                elastalert_logger.warning("Writing alert for rule %s without a stable id, so a retry may duplicate it: %r",
-                                          self.rule['detection_public_id'], e)
-                alert_id = uuid.uuid4().hex
-            try:
-                self.write(alert_id, self.payload(match))
-            except ElasticsearchException as e:
-                # EAException makes ElastAlert retry
-                raise EAException(f"Unable to write the alert to Elasticsearch: {str(e)[:ERROR_TEXT_LIMIT]}") from e
+            timestamp = strftime("%Y-%m-%d"'T'"%H:%M:%S"'.000Z', gmtime())
+            headers = {"Content-Type": "application/json"}
 
-    def payload(self, match):
-        rule_info = {
-            "name": self.rule['detection_title'],
-            "uuid": self.rule['detection_public_id']
-        }
+            creds = None
+            if 'es_username' in self.rule and 'es_password' in self.rule:
+                creds = (self.rule['es_username'], self.rule['es_password'])
 
-        # Add optional fields if they are present in the rule
-        for field in self.optional_fields:
-            rule_key = field.split('_')[-1]  # Assumes field format "sigma_<key>"
-            if field in self.rule:
-                rule_info[rule_key] = self.rule[field]
+            # Start building the rule dict
+            rule_info = {
+                "name": self.rule['detection_title'],
+                "uuid": self.rule['detection_public_id']
+            }
 
-        event_info = {
-            "kind": "alert",
-            "severity": self.rule['event.severity'],
-            "module": self.rule['event.module'],
-            "dataset": self.rule['event.dataset'],
-            "severity_label": self.rule['sigma_level']
-        }
+            # Add optional fields if they are present in the rule
+            for field in self.optional_fields:
+                rule_key = field.split('_')[-1]  # Assumes field format "sigma_<key>"
+                if field in self.rule:
+                    rule_info[rule_key] = self.rule[field]
 
-        payload = {
-            "tags": ["alert"],
-            "rule": rule_info,
-            "event": event_info,
-            "sigma_level": self.rule['sigma_level'],
-            "event_data": self.event_data(match),
-            "@timestamp": datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%S.000Z')
-        }
-
-        if self.is_correlation:
-            keys = self.query_keys()
-            try:
-                # built before any is added, so a failure adds none
-                reason = self.summary(match)
-                labels = {"correlation_group_by": ', '.join(keys), "correlation_group": self.group(match)} if keys else None
-                related = self.related(match)
-            except MATCH_ERRORS as e:
-                elastalert_logger.warning("Writing alert for rule %s without its correlation summary: %r",
-                                          self.rule['detection_public_id'], e)
-            else:
-                payload["event"]["reason"] = reason
-                if labels:
-                    payload["labels"] = labels
-                if related:
-                    payload["related"] = related
-
-        return payload
-
-    def write(self, alert_id, payload):
-        try:
-            self.create(alert_id, payload)
-        except RequestError as e:
-            # mapping rejections come from event_data; retry it as text
-            rejection = str(e)[:ERROR_TEXT_LIMIT]
-            try:
-                self.create(alert_id, self.without_event_data(payload, rejection))
-            except RequestError as again:
-                elastalert_logger.error("Dropping alert %s for rule %s, rejected by Elasticsearch even without its event data: %s; first rejection: %s",
-                                        alert_id, self.rule['detection_public_id'], str(again)[:ERROR_TEXT_LIMIT], rejection)
-                return
-            elastalert_logger.warning("Stored alert %s for rule %s with its event data as text, rejected by Elasticsearch: %s",
-                                      alert_id, self.rule['detection_public_id'], rejection)
-
-    def create(self, alert_id, payload):
-        try:
-            self.es.create(index=ALERT_INDEX, id=alert_id, body=payload)
-        except ConflictError:
-            pass  # a repeat id is already stored
-
-    @staticmethod
-    def without_event_data(payload, rejection):
-        """Moves event_data to event.original; the tag keeps Fleet's final pipeline from dropping it."""
-        fallback = {k: v for k, v in payload.items() if k != 'event_data'}
-        fallback['event'] = dict(payload['event'], original=json.dumps(payload['event_data'], cls=DateTimeEncoder))
-        fallback['error'] = {'message': f"event_data rejected by Elasticsearch: {rejection}"}
-        fallback['tags'] = payload['tags'] + ['preserve_original_event']
-        return fallback
+            # Construct the payload with the conditional rule_info
+            payload = {
+                "tags": "alert",
+                "rule": rule_info,
+                "event": {
+                    "severity": self.rule['event.severity'],
+                    "module": self.rule['event.module'],
+                    "dataset": self.rule['event.dataset'],
+                    "severity_label": self.rule['sigma_level']
+                },
+                "sigma_level": self.rule['sigma_level'],
+                "event_data": match,
+                "@timestamp": timestamp
+            }
+            url = f"https://{self.rule['es_host']}:{self.rule['es_port']}/logs-detections.alerts-so/_doc/"
+            requests.post(url, data=json.dumps(payload), headers=headers, verify=False, auth=creds)
 
     def get_info(self):
         return {'type': 'SecurityOnionESAlerter'}

salt/elastalert/files/modules/so/securityonion-es_test.py

@@ -1,260 +0,0 @@
-# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
-# https://securityonion.net/license; you may not use this file except in compliance with the
-# Elastic License 2.0.
-
-import copy
-from datetime import datetime, timezone
-import importlib.util
-import json
-import os
-import unittest
-from unittest.mock import MagicMock
-
-from elasticsearch.exceptions import ConflictError, ConnectionError, RequestError
-
-spec = importlib.util.spec_from_file_location('securityonion_es', os.path.join(os.path.dirname(__file__), 'securityonion-es.py'))
-es = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(es)
-
-BASE_RULE = {
-    'detection_title': 'Many Failed Network Logons To One Host From One Source',
-    'detection_public_id': '35a42db6-6629-45af-b8aa-e1fa33c28ef5',
-    'sigma_level': 'medium',
-    'sigma_correlation': 'event_count',
-    'event.severity': 3,
-    'event.module': 'sigma',
-    'event.dataset': 'sigma.alert',
-    'summary_template': '%count% failed network logons to %host.name% from %source.ip% in %duration%',
-}
-
-PLAIN_RULE = {k: v for k, v in BASE_RULE.items() if k not in ('sigma_correlation', 'summary_template')}
-
-
-def correlation_match():
-    return {
-        'event_count': 3561,
-        'window_start': '2026-09-30T18:05:10+00:00',
-        '@timestamp': '2026-09-30T18:07:53+00:00',
-        'host': {'name': 'host-01'},
-        'source': {'ip': '192.0.2.10'},
-        '_id': '6d1c',
-        'num_hits': 1,
-        'num_matches': 1,
-    }
-
-
-class TestSecurityOnionESAlerter(unittest.TestCase):
-
-    def creates(self, rule, match, effects=None):
-        """Run alert(); return (body, id) of each create."""
-        alerter = es.SecurityOnionESAlerter(rule)
-        alerter.es = MagicMock()
-        alerter.es.create.side_effect = effects
-        alerter.alert([match])
-        calls = alerter.es.create.call_args_list
-        self.assertTrue(all(c.kwargs['index'] == 'logs-detections.alerts-so' for c in calls))
-        return [(json.loads(json.dumps(c.kwargs['body'], cls=es.DateTimeEncoder)), c.kwargs['id']) for c in calls]
-
-    def send(self, rule, match):
-        """Run alert(); return the payload it wrote and its id."""
-        (payload, alert_id), = self.creates(rule, match)
-        return payload, alert_id
-
-    def test_compound_query_key_left_out_of_event_data(self):
-        rule = dict(BASE_RULE, compound_query_key=['host.name', 'source.ip'], query_key='host.name,source.ip')
-        match = correlation_match()
-        match['host.name,source.ip'] = 'host-01, 192.0.2.10'
-        original = copy.deepcopy(match)
-
-        payload, _ = self.send(rule, match)
-
-        self.assertNotIn('host.name,source.ip', payload['event_data'])
-        self.assertEqual(payload['event_data']['host'], {'name': 'host-01'})
-        self.assertEqual(payload['event_data']['source'], {'ip': '192.0.2.10'})
-        self.assertEqual(payload['rule'], {'name': BASE_RULE['detection_title'], 'uuid': BASE_RULE['detection_public_id'], 'correlation': 'event_count'})
-        self.assertEqual(payload['labels'], {'correlation_group_by': 'host.name, source.ip', 'correlation_group': 'host-01, 192.0.2.10'})
-        self.assertEqual(payload['related'], {'hosts': ['host-01'], 'ip': ['192.0.2.10']})
-        self.assertEqual(payload['event']['kind'], 'alert')
-        self.assertEqual(payload['event']['reason'], '3,561 failed network logons to host-01 from 192.0.2.10 in 2 minutes')
-        # ElastAlert reuses the match
-        self.assertEqual(match, original)
-
-    def test_single_query_key(self):
-        rule = dict(BASE_RULE, query_key='user.name', summary_template='%count% failed SOC logins for %user.name%')
-        match = {'event_count': 3, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
-                 'user': {'name': 'user@example.invalid'}}
-
-        payload, _ = self.send(rule, match)
-
-        self.assertEqual(payload['labels'], {'correlation_group_by': 'user.name', 'correlation_group': 'user@example.invalid'})
-        self.assertEqual(payload['related'], {'user': ['user@example.invalid']})
-        self.assertEqual(payload['event']['reason'], '3 failed SOC logins for user@example.invalid')
-        self.assertEqual(payload['event_data'], match)
-
-    def test_related_buckets(self):
-        rule = dict(BASE_RULE, compound_query_key=['winlog.event_data.TargetUserName', 'source.ip', 'dns.highest_registered_domain'],
-                    query_key='winlog.event_data.TargetUserName,source.ip,dns.highest_registered_domain')
-        match = correlation_match()
-        match.update({'winlog': {'event_data': {'TargetUserName': ['admin1', 'svc', 'admin1']}},
-                      'source': {'ip': 'not-an-ip'}, 'dns': {'highest_registered_domain': 'example.com'}})
-
-        payload, _ = self.send(rule, match)
-
-        # deduped; invalid IP skipped; domain stays in the group only
-        self.assertEqual(payload['related'], {'user': ['admin1', 'svc']})
-        self.assertEqual(payload['labels']['correlation_group'], "['admin1', 'svc', 'admin1'], not-an-ip, example.com")
-
-        payload, _ = self.send(dict(BASE_RULE, query_key='dns.highest_registered_domain'), match)
-
-        self.assertNotIn('related', payload)
-
-    def test_related_uses_original_spellings(self):
-        rule = dict(BASE_RULE, query_key='user.name', summary_template=None)
-        match = {'event_count': 3, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
-                 'user': {'name': 'admin', 'name_spellings': ['Admin', 'admin', 'ADMIN']}}
-
-        payload, _ = self.send(rule, match)
-
-        # the group shows the lowercased value; related.user finds every spelling
-        self.assertEqual(payload['labels']['correlation_group'], 'admin')
-        self.assertEqual(payload['related'], {'user': ['Admin', 'admin', 'ADMIN']})
-        self.assertEqual(payload['event']['reason'], '3 events for user.name admin in 8 seconds')
-
-    def test_plain_rule_has_no_correlation_fields(self):
-        # a query_key alone (e.g. from an override) isn't a correlation
-        rule = dict(PLAIN_RULE, query_key='user.name')
-        # ElastAlert parses @timestamp for EQL hits
-        match = {'@timestamp': datetime(2026, 9, 30, 16, 50, tzinfo=timezone.utc), '_id': 'abc',
-                 'process': {'name': 'whoami.exe'}, 'user': {'name': 'user'}}
-
-        payload, alert_id = self.send(rule, match)
-
-        alerter = es.SecurityOnionESAlerter(rule)
-        self.assertEqual(payload['rule'], {'name': PLAIN_RULE['detection_title'], 'uuid': PLAIN_RULE['detection_public_id']})
-        self.assertNotIn('labels', payload)
-        self.assertNotIn('related', payload)
-        self.assertNotIn('reason', payload['event'])
-        self.assertEqual(payload['event']['kind'], 'alert')
-        self.assertEqual(payload['event_data'], dict(match, **{'@timestamp': '2026-09-30T16:50:00+00:00'}))
-        self.assertEqual(alert_id, alerter.alert_id(match))
-        self.assertNotEqual(alerter.alert_id(match), alerter.alert_id(dict(match, _id='abd')))
-        self.assertNotEqual(alerter.alert_id(match), es.SecurityOnionESAlerter(dict(rule, detection_public_id='other')).alert_id(match))
-        # without an _id, never deduplicated
-        self.assertNotEqual(alerter.alert_id({'_id': None}), alerter.alert_id({'_id': None}))
-
-    def test_ungrouped_correlation_id_ignores_row_hash(self):
-        rule = dict(BASE_RULE, summary_template=None)
-        first = {k: v for k, v in correlation_match().items() if k not in ('host', 'source')}
-        # ES|QL hashes the row into _id, so a later count changes it
-        later = dict(first, event_count=3600, _id='9f2a')
-
-        payload, alert_id = self.send(rule, first)
-
-        alerter = es.SecurityOnionESAlerter(rule)
-        self.assertEqual(alerter.alert_id(first), alerter.alert_id(later))
-        self.assertNotEqual(alerter.alert_id(first), alerter.alert_id(dict(first, **{'@timestamp': '2026-09-30T18:09:00+00:00'})))
-        self.assertEqual(alert_id, alerter.alert_id(first))
-        self.assertEqual(payload['event']['reason'], '3,561 events in 2 minutes')
-        self.assertNotIn('labels', payload)
-
-    def test_temporal_count_column(self):
-        rule = dict(BASE_RULE, sigma_correlation='temporal', summary_template=None)
-        match = {'event_type_count': 2, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00'}
-
-        payload, _ = self.send(rule, match)
-
-        self.assertEqual(payload['event']['reason'], '2 correlated rules matched in 8 seconds')
-
-    def test_grouped_correlation_id_unchanged(self):
-        """Ids of alerts already written must not change."""
-        rule = dict(BASE_RULE, compound_query_key=['host.name', 'source.ip'], query_key='host.name,source.ip')
-        key = f"{BASE_RULE['detection_public_id']}|2026-09-30T18:07:53+00:00|host-01|192.0.2.10"
-
-        self.assertEqual(es.SecurityOnionESAlerter(rule).alert_id(correlation_match()), es.hashlib.sha256(key.encode()).hexdigest())
-
-    def test_rejected_event_data_is_kept_as_text(self):
-        rule = dict(BASE_RULE, query_key='user.name', summary_template='%count% failed SOC logins for %user.name%')
-        match = {'event_count': 3, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
-                 'user': {'name': 'user@example.invalid'}}
-        rejected = RequestError(400, 'document_parsing_exception', {})
-
-        (first, _), (second, _) = self.creates(rule, match, [rejected, None])
-
-        self.assertIn('event_data', first)
-        self.assertNotIn('event_data', second)
-        self.assertEqual(json.loads(second['event']['original']), match)
-        self.assertEqual(second['tags'], ['alert', 'preserve_original_event'])
-        self.assertEqual(first['tags'], ['alert'])
-        self.assertTrue(second['error']['message'].startswith('event_data rejected by Elasticsearch: '))
-        self.assertIn('document_parsing_exception', second['error']['message'])
-        # everything else carries over
-        self.assertEqual({k: v for k, v in second['event'].items() if k != 'original'}, first['event'])
-        changed = ('event_data', 'event', 'error', 'tags')
-        self.assertEqual({k: v for k, v in second.items() if k not in changed}, {k: v for k, v in first.items() if k not in changed})
-
-    def test_rejected_dates_are_kept_as_text(self):
-        match = {'@timestamp': datetime(2026, 9, 30, 16, 50, tzinfo=timezone.utc), '_id': 'abc'}
-
-        _, (second, _) = self.creates(PLAIN_RULE, match, [RequestError(400, 'document_parsing_exception', {}), None])
-
-        self.assertEqual(json.loads(second['event']['original']), {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'})
-
-    def test_rejected_twice_is_dropped_without_retry(self):
-        rejected = RequestError(400, 'document_parsing_exception', {})
-        match = {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'}
-
-        with self.assertLogs('elastalert', 'ERROR') as logs:
-            self.assertEqual(len(self.creates(PLAIN_RULE, match, [rejected, rejected])), 2)
-
-        self.assertIn('Dropping alert', logs.output[0])
-
-    def test_write_failure_is_retried(self):
-        match = {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'}
-
-        with self.assertRaisesRegex(es.EAException, 'Unable to write the alert to Elasticsearch'):
-            self.creates(PLAIN_RULE, match, [ConnectionError('N/A', 'refused', None)])
-
-    def test_repeat_id_is_ignored(self):
-        match = {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'}
-
-        self.assertEqual(len(self.creates(PLAIN_RULE, match, [ConflictError(409, 'version_conflict_engine_exception', {})])), 1)
-
-    def test_correlation_fields_are_optional(self):
-        rule = dict(BASE_RULE, query_key='source.ip')
-        # no window_start: the summary cannot be built
-        match = {k: v for k, v in correlation_match().items() if k != 'window_start'}
-
-        with self.assertLogs('elastalert', 'WARNING') as logs:
-            payload, _ = self.send(rule, match)
-
-        self.assertIn('without its correlation summary', logs.output[0])
-        self.assertEqual(payload['event']['kind'], 'alert')
-        self.assertNotIn('reason', payload['event'])
-        self.assertNotIn('labels', payload)
-        self.assertNotIn('related', payload)
-
-    def test_unstable_id_still_writes(self):
-        # no @timestamp: the window end is unknown
-        match = {k: v for k, v in correlation_match().items() if k not in ('@timestamp', 'window_start')}
-
-        with self.assertLogs('elastalert', 'WARNING') as logs:
-            payload, alert_id = self.send(BASE_RULE, match)
-
-        self.assertIn('without a stable id', logs.output[0])
-        self.assertEqual(len(alert_id), 32)
-        self.assertEqual(payload['event_data'], match)
-
-    def test_summary_formats_values(self):
-        rule = dict(BASE_RULE, sigma_correlation='value_avg', query_key='source.ip',
-                    summary_template='%count% for %source.ip% to %destination.port% %no.such.field%')
-        match = {'value_avg': 2.5, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
-                 'source': {'ip': '192.0.2.10'}, 'destination': {'port': [22, 80, 443, 8080, 8443]}}
-
-        payload, _ = self.send(rule, match)
-
-        self.assertEqual(payload['event']['reason'], '2.50 for 192.0.2.10 to 22, 80, 443 and 2 more %no.such.field%')
-        self.assertEqual(es.SecurityOnionESAlerter.format_count('n/a'), 'n/a')
-
-    def test_get_info(self):
-        self.assertEqual(es.SecurityOnionESAlerter(PLAIN_RULE).get_info(), {'type': 'SecurityOnionESAlerter'})

salt/elastalert/soc_elastalert.yaml

@@ -120,7 +120,7 @@ elastalert:
         helpLink: elastalert
     old_query_limit:
       minutes:
-        description: How long ElastAlert can be down, in minutes, and still resume each rule where it stopped. After a longer outage, rules restart from now and skip the gap.
+        description: Amount of time in minutes between queries to start at the most recently run query.
         global: True
         helpLink: elastalert
     es_conn_timeout:

salt/elastic-fleet-package-registry/config.sls

@@ -19,7 +19,6 @@ elastic-agent-pr:
     - gid: 948
     - home: /opt/so/conf/elastic-fleet-pr
     - createhome: False
-    - shell: /sbin/nologin
 
 {% else %}
 

salt/elastic-fleet-package-registry/enabled.sls

@@ -6,11 +6,9 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 
 include:
-  - ca.trust
   - elastic-fleet-package-registry.config
   - elastic-fleet-package-registry.sostatus
 
@@ -36,9 +34,8 @@ so-elastic-fleet-package-registry:
       {% for BINDING in DOCKERMERGED.containers['so-elastic-fleet-package-registry'].port_bindings %}
       - {{ BINDING }}
       {% endfor %}
-    - binds:
-      - {{ CATRUST.pem }}:/etc/ssl/certs/ca-certificates.crt:ro
     {% if DOCKERMERGED.containers['so-elastic-fleet-package-registry'].custom_bind_mounts %}
+    - binds:
         {% for BIND in DOCKERMERGED.containers['so-elastic-fleet-package-registry'].custom_bind_mounts %}
       - {{ BIND }}
         {% endfor %}
@@ -55,8 +52,6 @@ so-elastic-fleet-package-registry:
       - {{ ULIMIT.name }}={{ ULIMIT.soft }}:{{ ULIMIT.hard }}
     {%   endfor %}
     {% endif %}
-    - watch:
-      - cmd: ca_trust_extract
 
 wait_for_so-elastic-fleet-package-registry:
   http.wait_for_successful_query:

salt/elasticagent/config.sls

@@ -20,7 +20,6 @@ elastic-agent:
     - gid: 949
     - home: /opt/so/conf/elastic-agent
     - createhome: False
-    - shell: /sbin/nologin
 
 elasticagentconfdir:
   file.directory:
@@ -40,8 +39,8 @@ elasticagent_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticagent/tools/sbin_jinja
-    - user: root
-    - group: root
+    - user: 949
+    - group: 939
     - file_mode: 755
     - template: jinja
 

salt/elasticagent/enabled.sls

@@ -6,7 +6,6 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 
 include:
@@ -38,7 +37,6 @@ so-elastic-agent:
       - {{ BINDING }}
       {% endfor %}
     - binds:
-      - {{ CATRUST.dir }}
       - /opt/so/conf/elastic-agent/elastic-agent.yml:/usr/share/elastic-agent/elastic-agent.yml:ro
       - /opt/so/log/elasticagent:/usr/share/elastic-agent/logs
       - /etc/pki/tls/certs/intca.crt:/etc/pki/tls/certs/intca.crt:ro 
@@ -67,7 +65,6 @@ so-elastic-agent:
       - file: create-elastic-agent-config
       - file: trusttheca
     - watch:
-      - cmd: ca_trust_extract
       - file: create-elastic-agent-config
       - file: trusttheca
 

salt/elasticfleet/config.sls

@@ -26,14 +26,13 @@ elastic-fleet:
     - gid: 947
     - home: /opt/so/conf/elastic-fleet
     - createhome: False
-    - shell: /sbin/nologin
 
 elasticfleet_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin
-    - user: root
-    - group: root
+    - user: 947
+    - group: 939
     - file_mode: 755
     - show_changes: False
 
@@ -41,8 +40,8 @@ elasticfleet_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin_jinja
-    - user: root
-    - group: root
+    - user: 947
+    - group: 939 
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -82,8 +81,8 @@ eapackageupgrade:
   file.managed:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
     - source: salt://elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-upgrade
-    - user: root
-    - group: root
+    - user: 947
+    - group: 939
     - mode: 755
     - template: jinja
 

salt/elasticfleet/enabled.sls

@@ -6,7 +6,6 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   from 'elasticfleet/map.jinja' import ELASTICFLEETMERGED %}
 
@@ -64,7 +63,6 @@ so-elastic-fleet:
       - {{ BINDING }}
       {% endfor %}
     - binds:
-      - {{ CATRUST.dir }}
       - /etc/pki/elasticfleet-server.crt:/etc/pki/elasticfleet-server.crt:ro
       - /etc/pki/elasticfleet-server.key:/etc/pki/elasticfleet-server.key:ro
       - /etc/pki/tls/certs/intca.crt:/etc/pki/tls/certs/intca.crt:ro
@@ -97,7 +95,6 @@ so-elastic-fleet:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: trusttheca
       - x509: etc_elasticfleet_key
       - x509: etc_elasticfleet_crt

salt/elasticfleet/files/integrations/grid-nodes_general/import-evtx-logs.json

@@ -29,7 +29,7 @@
               "\\.gz$"
             ],
             "include_files": [],
-            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- add_fields:\n    target: event\n    fields:\n      dataset: windows.forwarded\n      module: windows\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: import.evtx\n- if:\n    equals:\n      winlog.channel: 'Security'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.security\n          module: system\n- if:\n    equals:\n      winlog.channel: 'Windows PowerShell'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell\n          module: windows\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n          module: system\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n          module: system\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n- add_fields:\n    target: data_stream\n    fields:\n        type: logs\n        dataset: import",
+            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.22.3\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.9.0\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.22.3\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.22.3\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.9.0\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
             "tags": [
               "import"
             ],

salt/elasticfleet/install_agent_grid.sls

@@ -14,8 +14,8 @@ so-elastic-agent-install:
   file.managed:
     - name: /usr/sbin/so-elastic-agent-install
     - source: salt://elasticfleet/tools/sbin/so-elastic-agent-install
-    - user: root
-    - group: root
+    - user: 947
+    - group: 939
     - mode: 755
     - show_changes: False
 

salt/elasticfleet/integration-defaults.map.jinja

@@ -30,6 +30,8 @@
     'azure_metrics.monitor': 'azure.monitor',
     'azure_metrics.storage_account': 'azure.storage_account',
     'azure_openai.metrics': 'azure.open_ai',
+    'beat.state': 'beats.stack_monitoring.state',
+    'beat.stats': 'beats.stack_monitoring.stats',
     'enterprisesearch.health': 'enterprisesearch.stack_monitoring.health',
     'enterprisesearch.stats': 'enterprisesearch.stack_monitoring.stats',
     'kibana.cluster_actions': 'kibana.stack_monitoring.cluster_actions',
@@ -38,8 +40,7 @@
     'kibana.node_rules': 'kibana.stack_monitoring.node_rules',
     'kibana.stats': 'kibana.stack_monitoring.stats',
     'kibana.status': 'kibana.stack_monitoring.status',
-    'logstash.node': 'logstash.stack_monitoring.node',
-    'logstash.node_cel': 'logstash.node',
+    'logstash.node_cel': 'logstash.stack_monitoring.node',
     'logstash.node_stats': 'logstash.stack_monitoring.node_stats',
     'synthetics.browser': 'synthetics-browser',
     'synthetics.browser_network': 'synthetics-browser.network',

salt/elasticfleet/tools/sbin/so-elastic-fleet-common

@@ -30,56 +30,6 @@ fleet_api() {
     curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/${QUERYPATH}" "$@" --retry 3 --retry-delay 10 --fail 2>/dev/null
 }
 
-elastic_fleet_require_agent_policy() {
-    local AGENT_POLICY=$1
-    local POLICY_JSON
-
-    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY") || [ -z "$POLICY_JSON" ]; then
-        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
-        return 1
-    fi
-
-    if ! jq -e '.item.package_policies | type == "array"' <<<"$POLICY_JSON" >/dev/null 2>&1; then
-        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
-        return 1
-    fi
-
-    echo "$POLICY_JSON"
-}
-
-# Print the single active enrollment token for POLICY_ID.
-# Exit 1: retryable (API failure, invalid response, no active token)
-# Exit 2: multiple active tokens - Shouldn't get into this state without manual intervention
-elastic_fleet_active_enrollment_token() {
-    local POLICY_ID=$1
-    local RESP TOKEN_COUNT API_KEY
-
-    if ! RESP=$(fleet_api "enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
-        echo "Error: Failed to retrieve enrollment tokens for agent policy '$POLICY_ID'." >&2
-        return 1
-    fi
-
-    if ! jq -e '.list' <<<"$RESP" >/dev/null 2>&1; then
-        echo "Error: Invalid enrollment token response for agent policy '$POLICY_ID'." >&2
-        return 1
-    fi
-
-    TOKEN_COUNT=$(jq --arg pid "$POLICY_ID" '[.list[] | select(.policy_id == $pid and .active == true)] | length' <<<"$RESP")
-
-    if [ "${TOKEN_COUNT:-0}" -eq 0 ]; then
-        echo "Error: No active enrollment token found for agent policy '$POLICY_ID'." >&2
-        return 1
-    fi
-
-    if [ "$TOKEN_COUNT" -gt 1 ]; then
-        echo "Error: Found $TOKEN_COUNT active enrollment tokens for agent policy '$POLICY_ID'; expected exactly one." >&2
-        return 2
-    fi
-
-    API_KEY=$(jq -r --arg pid "$POLICY_ID" '.list[] | select(.policy_id == $pid and .active == true) | .api_key' <<<"$RESP")
-    echo "$API_KEY"
-}
-
 # Max number of concurrent Fleet write jobs (create/update). Override via env if needed.
 MAX_FLEET_JOBS=${MAX_FLEET_JOBS:-10}
 
@@ -112,7 +62,15 @@ elastic_fleet_load_integrations_dir() {
     i=0
 
     # Fetch the agent policy a single time; we look up integration ids locally below.
-    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        echo "Error: Failed to retrieve agent policy '$AGENT_POLICY'."
+        rm -f "$FAIL_FILE"
+        rm -rf "$OUT_DIR"
+        return 1
+    fi
+
+    if ! jq -e '.item.package_policies' <<<"$POLICY_JSON" >/dev/null 2>&1; then
+        echo "Error: Invalid agent policy response for '$AGENT_POLICY'."
         rm -f "$FAIL_FILE"
         rm -rf "$OUT_DIR"
         return 1
@@ -166,15 +124,9 @@ elastic_fleet_integration_check() {
 
     JSON_STRING=$2
 
-    NAME=$(jq -r .name "$JSON_STRING")
-    INTEGRATION_ID=""
+    NAME=$(jq -r .name $JSON_STRING)
 
-    local POLICY_JSON
-    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
-        return 1
-    fi
-
-    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
+    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
 
 }
 
@@ -196,16 +148,7 @@ elastic_fleet_integration_remove() {
 
     NAME=$2
 
-    local POLICY_JSON
-    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
-        return 1
-    fi
-
-    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
-    if [ -z "$INTEGRATION_ID" ]; then
-        echo "Error: Integration '$NAME' was not found in agent policy '$AGENT_POLICY'." >&2
-        return 1
-    fi
+    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
 
     JSON_STRING=$( jq -n \
                     --arg INTEGRATIONID "$INTEGRATION_ID" \

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-defend

@@ -13,10 +13,7 @@ ERROR=false
 for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/elastic-defend/*.json
 do
   printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
-  if ! elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"; then
-    ERROR=true
-    continue
-  fi
+  elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
   if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Upgrading integration policy\n"
       if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server

@@ -7,35 +7,20 @@
 . /usr/sbin/so-elastic-fleet-common
 
 # Get all the fleet policies
-if ! json_output=$(fleet_api "agent_policies" -H 'kbn-xsrf: true'); then
-    echo "Error: Failed to retrieve Fleet agent policies." >&2
-    exit 1
-fi
-
-if ! jq -e '.items' <<<"$json_output" >/dev/null 2>&1; then
-    echo "Error: Invalid Fleet agent policies response." >&2
-    exit 1
-fi
+json_output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -L -X GET "localhost:5601/api/fleet/agent_policies" -H 'kbn-xsrf: true')
 
 # Extract the IDs that start with "FleetServer_"
-POLICY=$(jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id' <<<"$json_output")
+POLICY=$(echo "$json_output" | jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id')
 
 # Iterate over each ID in the POLICY variable
 for POLICYNAME in $POLICY; do
     printf "\nUpdating Policy: $POLICYNAME\n"
 
-    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$POLICYNAME"); then
-        exit 1
-    fi
-
-    INTEGRATION_ID=$(jq -r '.item.package_policies[]? | select(.package.name == "fleet_server") | .id' <<<"$POLICY_JSON")
-    if [ -z "$INTEGRATION_ID" ]; then
-        echo "Error: fleet_server integration was not found in agent policy '$POLICYNAME'." >&2
-        exit 1
-    fi
+    # First get the Integration ID
+    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$POLICYNAME" | jq -r '.item.package_policies[] | select(.package.name == "fleet_server") | .id')  
 
     # Modify the default integration policy to update the policy_id and an with the correct naming
-    UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
+	UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
     .policy_id = $policy_id |
     .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 

salt/elasticfleet/tools/sbin_jinja/so-elastic-agent-gen-installers

@@ -22,19 +22,12 @@ NUM_RUNNING=$(pgrep -cf "/bin/bash /sbin/so-elastic-agent-gen-installers")
 
 for i in {1..30}
 do
-   ENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial")
-   TOKEN_RC=$?
-   if [ "$TOKEN_RC" -eq 2 ]; then
-     exit 1
-   fi
+   ENROLLMENTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
    FLEETHOST=$(curl -K /opt/so/conf/elasticsearch/curl.config 'http://localhost:5601/api/fleet/fleet_server_hosts/grid-default' | jq -r  '.item.host_urls[]' | paste -sd ',')
-   if [[ -n "$FLEETHOST" ]] && [[ -n "$ENROLLMENTOKEN" ]]; then
-     break
-   fi
-   sleep 10
+if [[ $FLEETHOST ]] && [[  $ENROLLMENTOKEN ]]; then break; else sleep 10; fi
 done
 
-if [[ -z "$FLEETHOST" ]] || [[ -z "$ENROLLMENTOKEN" ]]; then
+if [[ -z $FLEETHOST ]] || [[ -z $ENROLLMENTOKEN ]]; then 
   printf "\nFleet Host URL, Enrollment Token or Elastic Version empty - exiting..."
   printf "\nFleet Host: $FLEETHOST, Enrollment Token: $ENROLLMENTOKEN\n"
   exit 1
@@ -74,25 +67,19 @@ for GOOS in "${GOTARGETOS[@]}"; do
     GOARCH="amd64"
     if [[ $GOOS == 'darwin/arm64' ]]; then GOOS="darwin" && GOARCH="arm64"; fi
     printf "\n\n### Generating $GOOS/$GOARCH Installer...\n"
-    if ! docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
+    docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
     --mount type=bind,source=/etc/pki/tls/certs/,target=/workspace/files/cert/ \
     --mount type=bind,source=/nsm/elastic-agent-workspace/,target=/workspace/files/elastic-agent/ \
     --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ \
-    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}; then
-        printf "\n### ERROR: Failed to generate $GOOS/$GOARCH installer. Exiting...\n"
-        exit 1
-    fi
+    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}
     printf "\n### $GOOS/$GOARCH Installer Generated...\n"
 done
 
 printf "\n\n### Generating MSI...\n"
 cp /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64 /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64.exe
-if ! docker run \
+docker run \
 --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ -w /output \
-{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs; then
-    printf "\n### ERROR: Failed to generate MSI. Exiting...\n"
-    exit 1
-fi
+{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs
 printf "\n### MSI Generated...\n"
 
 # Verify installers were created

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-setup

@@ -202,9 +202,26 @@ fi
 ### Finalization ###
 
 # Query for Enrollment Tokens for default policies
-ENDPOINTSENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial") || exit 1
-GRIDNODESENROLLMENTOKENGENERAL=$(elastic_fleet_active_enrollment_token "so-grid-nodes_general") || exit 1
-GRIDNODESENROLLMENTOKENHEAVY=$(elastic_fleet_active_enrollment_token "so-grid-nodes_heavy") || exit 1
+if ENDPOINTSENROLLMENTOKEN_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    ENDPOINTSENROLLMENTOKEN=$(echo "$ENDPOINTSENROLLMENTOKEN_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
+else
+    echo -e "\nFailed to query for Endpoints enrollment token"
+    exit 1
+fi
+
+if GRIDNODESENROLLMENTOKENGENERAL_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    GRIDNODESENROLLMENTOKENGENERAL=$(echo "$GRIDNODESENROLLMENTOKENGENERAL_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_general")) | .api_key')
+else
+    echo -e "\nFailed to query for Grid nodes - General enrollment token"
+    exit 1
+fi
+
+if GRIDNODESENROLLMENTOKENHEAVY_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    GRIDNODESENROLLMENTOKENHEAVY=$(echo "$GRIDNODESENROLLMENTOKENHEAVY_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_heavy")) | .api_key')
+else
+    echo -e "\nFailed to query for Grid nodes - Heavy enrollment token"
+    exit 1
+fi
 
 # Store needed data in minion pillar
 pillar_file=/opt/so/saltstack/local/pillar/minions/{{ GLOBALS.minion_id }}.sls

salt/elasticsearch/ca.sls

@@ -0,0 +1,49 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at 
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+{% from 'allowed_states.map.jinja' import allowed_states %}
+{% if sls.split('.')[0] in allowed_states or sls in allowed_states %}
+{%   from 'vars/globals.map.jinja' import GLOBALS %}
+
+# Move our new CA over so Elastic and Logstash can use SSL with the internal CA
+catrustdir:
+  file.directory:
+    - name: /opt/so/conf/ca
+    - user: 939
+    - group: 939
+    - makedirs: True
+
+{%   if GLOBALS.is_manager %}
+# We have to add the Manager CA to the CA list
+catrustscript:
+  cmd.script:
+    - source: salt://elasticsearch/tools/sbin_jinja/so-catrust
+    - template: jinja
+    - cwd: /opt/so
+    - defaults:
+        GLOBALS: {{ GLOBALS }}
+{%   endif %}
+
+elasticsearch_cacerts:
+  file.managed:
+    - name: /opt/so/conf/ca/cacerts
+    - source: salt://elasticsearch/cacerts
+    - user: 939
+    - group: 939
+
+elasticsearch_capems:
+  file.managed:
+    - name: /opt/so/conf/ca/tls-ca-bundle.pem
+    - source: salt://elasticsearch/tls-ca-bundle.pem
+    - user: 939
+    - group: 939
+
+{% else %}
+
+{{sls}}_state_not_allowed:
+  test.fail_without_changes:
+    - name: {{sls}}_state_not_allowed
+
+{% endif %}

salt/elasticsearch/cluster.sls

@@ -107,12 +107,6 @@ so-elasticsearch-system-indices-patch:
       - file: so-elasticsearch-system-indices-patch-script
 {%  endif %}
 
-so-elasticsearch-ilm-policy-reload:
-  file.absent:
-    - name: /opt/so/state/esilm.txt
-    - onchanges:
-      - file: so-elasticsearch-ilm-policy-load-script
-
 # heavynodes will only load ILM policies for SO managed indices. (Indicies defined in elasticsearch/defaults.yaml)
 so-elasticsearch-ilm-policy-load:
   cmd.run:
@@ -121,9 +115,8 @@ so-elasticsearch-ilm-policy-load:
     - require:
       - docker_container: so-elasticsearch
       - file: so-elasticsearch-ilm-policy-load-script
-      - http: wait_for_so-elasticsearch
-      - file: so-elasticsearch-ilm-policy-reload
-    - unless: test -f /opt/so/state/esilm.txt
+    - onchanges:
+      - file: so-elasticsearch-ilm-policy-load-script
 
 so-elasticsearch-templates-reload:
   file.absent:

salt/elasticsearch/config.sls

@@ -32,14 +32,13 @@ elasticsearch:
     - gid: 930
     - home: /opt/so/conf/elasticsearch
     - createhome: False
-    - shell: /sbin/nologin
 
 elasticsearch_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin
-    - user: root
-    - group: root
+    - user: 930
+    - group: 939
     - file_mode: 755
     - exclude_pat:
       - so-elasticsearch-pipelines # exclude this because we need to watch it for changes, we sync it in another state
@@ -50,8 +49,8 @@ so-elasticsearch-system-indices-patch-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-system-indices-patch
     - source: salt://elasticsearch/tools/sbin/so-elasticsearch-system-indices-patch
-    - user: root
-    - group: root
+    - user: 930
+    - group: 939
     - mode: 755
     - show_changes: False
 
@@ -59,8 +58,8 @@ elasticsearch_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin_jinja
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939 
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -73,8 +72,8 @@ so-elasticsearch-ilm-policy-load-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-ilm-policy-load
     - source: salt://elasticsearch/tools/sbin_jinja/so-elasticsearch-ilm-policy-load
-    - user: root
-    - group: root
+    - user: 930
+    - group: 939
     - mode: 754
     - template: jinja
     - defaults:
@@ -85,8 +84,8 @@ so-elasticsearch-pipelines-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-pipelines
     - source: salt://elasticsearch/tools/sbin/so-elasticsearch-pipelines
-    - user: root
-    - group: root
+    - user: 930
+    - group: 939
     - mode: 754
     - show_changes: False
 

salt/elasticsearch/defaults.yaml

@@ -1,7 +1,7 @@
 elasticsearch:
   enabled: false
   esheap: '600m'
-  version: 9.4.8
+  version: 9.4.5
   index_clean: true
   data_retention_method: DLM
   vm:
@@ -1160,7 +1160,6 @@ elasticsearch:
         - so-fleet_agent_id_verification-1
         - so-logs-mappings
         - so-logs-settings
-        - detections-alerts-mappings
         data_stream:
           allow_custom_routing: false
           hidden: false
@@ -3310,7 +3309,6 @@ elasticsearch:
         composed_of:
         - event-mappings
         - logs-system.security@package
-        - so-fleet_system.security_caseless-1
         - logs-system.security@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4177,7 +4175,6 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.forwarded@package
-        - so-fleet_process_caseless-1
         - logs-windows.forwarded@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4227,7 +4224,6 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.powershell@package
-        - so-fleet_process_caseless-1
         - logs-windows.powershell@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4277,7 +4273,6 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.powershell_operational@package
-        - so-fleet_process_caseless-1
         - logs-windows.powershell_operational@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4327,7 +4322,6 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.sysmon_operational@package
-        - so-fleet_process_caseless-1
         - logs-windows.sysmon_operational@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1

salt/elasticsearch/enabled.sls

@@ -6,7 +6,6 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCH_NODES %}
 {%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCH_SEED_HOSTS %}
@@ -14,6 +13,7 @@
 
 include:
   - ca
+  - elasticsearch.ca
   - elasticsearch.ssl
   - elasticsearch.config
   - elasticsearch.sostatus
@@ -63,14 +63,15 @@ so-elasticsearch:
       - {{ BINDING }}
       {% endfor %}
     - binds:
-      - {{ CATRUST.dir }}
       - /opt/so/conf/elasticsearch/elasticsearch.yml:/usr/share/elasticsearch/config/elasticsearch.yml:ro
       - /opt/so/conf/elasticsearch/log4j2.properties:/usr/share/elasticsearch/config/log4j2.properties:ro
       - /nsm/elasticsearch:/usr/share/elasticsearch/data:rw
       - /opt/so/log/elasticsearch:/var/log/elasticsearch:rw
+      - /opt/so/conf/ca/cacerts:/usr/share/elasticsearch/jdk/lib/security/cacerts:ro
       - /etc/pki/tls/certs/intca.crt:/usr/share/elasticsearch/config/ca.crt:ro
       - /etc/pki/elasticsearch.crt:/usr/share/elasticsearch/config/elasticsearch.crt:ro
       - /etc/pki/elasticsearch.key:/usr/share/elasticsearch/config/elasticsearch.key:ro
+      - /etc/pki/elasticsearch.p12:/usr/share/elasticsearch/config/elasticsearch.p12:ro
       - /opt/so/conf/elasticsearch/users_roles:/usr/share/elasticsearch/config/users_roles:ro
       - /opt/so/conf/elasticsearch/users:/usr/share/elasticsearch/config/users:ro
       {% if ELASTICSEARCHMERGED.config.path.get('repo', False) %}
@@ -84,19 +85,21 @@ so-elasticsearch:
         {% endfor %}
       {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: trusttheca
       - x509: elasticsearch_crt
       - x509: elasticsearch_key
+      - file: elasticsearch_cacerts
       - file: esyml
     - require:
       - file: trusttheca
       - x509: elasticsearch_crt
       - x509: elasticsearch_key
+      - file: elasticsearch_cacerts
       - file: esyml
       - file: eslog4jfile
       - file: nsmesdir
       - file: eslogdir
+      - file: elasticp12perms
       - cmd: auth_users_roles_inode
       - cmd: auth_users_inode
 

salt/elasticsearch/files/ingest/global@custom

@@ -1,5 +1,5 @@
 {
-    "version": 4,
+    "version": 3,
     "_meta": {
         "managed_by": "securityonion",
         "managed": true
@@ -99,7 +99,7 @@
         },
         {
             "set": {
-                "if": "ctx.tags != null && ctx.tags.contains('import') && ctx._index != null && ctx._index.startsWith('logs-import-')",
+                "if": "ctx.tags != null && ctx.tags.contains('import')",
                 "override": true,
                 "field": "data_stream.dataset",
                 "value": "import"
@@ -107,7 +107,7 @@
         },
         {
             "set": {
-                "if": "ctx.tags != null && ctx.tags.contains('import') && ctx._index != null && ctx._index.startsWith('logs-import-')",
+                "if": "ctx.tags != null && ctx.tags.contains('import')",
                 "override": true,
                 "field": "data_stream.namespace",
                 "value": "so"
@@ -177,32 +177,6 @@
                 "description": "Extract IPs from Elastic Agent events (host.ip) and adds them to related.ip"
             }
         },
-        {
-            "trim": {
-                "if": "ctx.event?.dataset == 'system.auth'",
-                "description": "Grok leaves a leading space on 'invalid user' names (elastic/integrations#12174) and, before 2.23.2, sudo padding",
-                "field": "user.name",
-                "ignore_missing": true,
-                "ignore_failure": true
-            }
-        },
-        {
-            "trim": {
-                "if": "ctx.event?.dataset == 'system.auth'",
-                "description": "Appended from the untrimmed user.name",
-                "field": "related.user",
-                "ignore_missing": true,
-                "ignore_failure": true
-            }
-        },
-        {
-            "script": {
-                "if": "ctx.event?.dataset == 'system.auth' && ctx.related?.user instanceof List",
-                "description": "Dedupe after trimming",
-                "source": "ctx.related.user = new ArrayList(new LinkedHashSet(ctx.related.user));",
-                "ignore_failure": true
-            }
-        },
         {
             "script": {
                 "description": "Snapshot event.ingested into _tmp.event_ingested_pre_fleet before .fleet_final_pipeline-1 overwrites it with ES ingest time",

salt/elasticsearch/files/ingest/import.evtx

@@ -1,31 +0,0 @@
-{
-  "description" : "import.evtx: normalize imported EVTX and reroute to logs-<dataset>-import",
-  "processors" : [
-    { "script":  {
-        "description": "Host from the event, not the importing node",
-        "lang": "painless",
-        "source": "Map host = ['os': ['type': 'windows', 'family': 'windows', 'platform': 'windows']]; def cn = ctx.winlog?.computer_name; if (cn != null && cn.toString().length() > 0) { String name = cn.toString(); int dot = name.indexOf('.'); if (dot > 0) { name = name.substring(0, dot); } host.put('hostname', name); host.put('name', name.toLowerCase()); } ctx.host = host;"
-    } },
-    { "script":  {
-        "description": "String event IDs, as Winlogbeat sends",
-        "lang": "painless",
-        "source": "if (ctx.winlog?.event_id != null) { ctx.winlog.event_id = ctx.winlog.event_id.toString(); } if (ctx.event?.code != null) { ctx.event.code = ctx.event.code.toString(); }"
-    } },
-    { "script":  {
-        "description": "Unnamed <Data> to param1..N, as Winlogbeat",
-        "lang": "painless",
-        "if": "ctx.winlog?.event_data?.Data instanceof Map && ctx.winlog.event_data.Data['#text'] != null",
-        "source": "def t = ctx.winlog.event_data.Data['#text']; List vals = t instanceof List ? t : [t]; for (int i = 0; i < vals.size(); i++) { ctx.winlog.event_data['param' + (i + 1)] = vals.get(i); } ctx.winlog.event_data.remove('Data');"
-    } },
-    { "script":  {
-        "description": "String values and LF line endings, as Winlogbeat",
-        "lang": "painless",
-        "if": "ctx.winlog?.event_data instanceof Map || ctx.winlog?.user_data instanceof Map",
-        "source": "String lf = String.valueOf((char) 10); String crlf = String.valueOf((char) 13) + lf; for (def key : ['event_data', 'user_data']) { def m = ctx.winlog[key]; if (!(m instanceof Map)) { continue; } for (def e : m.entrySet()) { def v = e.getValue(); if (v instanceof String) { e.setValue(v.replace(crlf, lf)); } else if (v instanceof Number || v instanceof Boolean) { e.setValue(v.toString()); } } }"
-    } },
-    { "set":     { "description": "event.kind, as Winlogbeat", "field": "event.kind", "value": "event", "override": false } },
-    { "set":     { "field": "data_stream.dataset", "copy_from": "event.dataset", "override": true, "ignore_empty_value": true } },
-    { "set":     { "field": "data_stream.namespace", "value": "import", "override": true } },
-    { "reroute": { "dataset": "{{data_stream.dataset}}", "namespace": "{{data_stream.namespace}}" } }
-  ]
-}

salt/elasticsearch/files/ingest/suricata.fileinfo

@@ -5,8 +5,7 @@
     { "rename": 	{ "field": "message2.proto", 			"target_field": "network.transport",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.app_proto", 		"target_field": "network.protocol",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.filename", 	"target_field": "file.name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "suricata.fileinfo.gaps",	"ignore_missing": true 	} },
-    { "set":		{ "if": "ctx.suricata?.fileinfo?.gaps == false", 	"field": "file.bytes.missing",	"value": 0 		} },
+    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "file.bytes.missing",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.magic", 		"target_field": "file.mime_type",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.md5", 		"target_field": "hash.md5",		"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.sha1", 		"target_field": "hash.sha1",		"ignore_missing": true 	} },

salt/elasticsearch/ssl.sls

@@ -38,6 +38,10 @@ elasticsearch_crt:
     - retry:
         attempts: 5
         interval: 30
+  cmd.run:
+    - name: "/usr/bin/openssl pkcs12 -inkey /etc/pki/elasticsearch.key -in /etc/pki/elasticsearch.crt -export -out /etc/pki/elasticsearch.p12 -nodes -passout pass:"
+    - onchanges:
+      - x509: /etc/pki/elasticsearch.key
 
 elastickeyperms:
   file.managed:
@@ -46,6 +50,13 @@ elastickeyperms:
     - mode: 640
     - group: 930
     
+elasticp12perms:
+  file.managed:
+    - replace: False
+    - name: /etc/pki/elasticsearch.p12
+    - mode: 640
+    - group: 930
+
 {% else %}
 
 {{sls}}_state_not_allowed:

salt/elasticsearch/templates/component/elastic-agent/so-fleet_process_caseless-1.json

@@ -1,123 +0,0 @@
-{
-  "_meta": {
-    "managed_by": "security_onion",
-    "managed": true,
-    "description": "Adds .caseless for Lucene queries. Restates each field's package type and .text."
-  },
-  "template": {
-    "mappings": {
-      "properties": {
-        "process": {
-          "properties": {
-            "executable": {
-              "type": "keyword",
-              "ignore_above": 1024,
-              "fields": {
-                "caseless": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "normalizer": "lowercase"
-                },
-                "text": {
-                  "type": "match_only_text"
-                }
-              }
-            },
-            "name": {
-              "type": "keyword",
-              "ignore_above": 1024,
-              "fields": {
-                "caseless": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "normalizer": "lowercase"
-                },
-                "text": {
-                  "type": "match_only_text"
-                }
-              }
-            },
-            "command_line": {
-              "type": "wildcard",
-              "ignore_above": 1024,
-              "fields": {
-                "caseless": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "normalizer": "lowercase"
-                },
-                "text": {
-                  "type": "match_only_text"
-                }
-              }
-            },
-            "parent": {
-              "properties": {
-                "executable": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "fields": {
-                    "caseless": {
-                      "type": "keyword",
-                      "ignore_above": 1024,
-                      "normalizer": "lowercase"
-                    },
-                    "text": {
-                      "type": "match_only_text"
-                    }
-                  }
-                },
-                "name": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "fields": {
-                    "caseless": {
-                      "type": "keyword",
-                      "ignore_above": 1024,
-                      "normalizer": "lowercase"
-                    },
-                    "text": {
-                      "type": "match_only_text"
-                    }
-                  }
-                },
-                "command_line": {
-                  "type": "wildcard",
-                  "ignore_above": 1024,
-                  "fields": {
-                    "caseless": {
-                      "type": "keyword",
-                      "ignore_above": 1024,
-                      "normalizer": "lowercase"
-                    },
-                    "text": {
-                      "type": "match_only_text"
-                    }
-                  }
-                }
-              }
-            }
-          }
-        },
-        "file": {
-          "properties": {
-            "path": {
-              "type": "keyword",
-              "ignore_above": 1024,
-              "fields": {
-                "caseless": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "normalizer": "lowercase"
-                },
-                "text": {
-                  "type": "match_only_text"
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  }
-}

salt/elasticsearch/templates/component/elastic-agent/so-fleet_system.security_caseless-1.json

@@ -1,80 +0,0 @@
-{
-  "_meta": {
-    "managed_by": "security_onion",
-    "managed": true,
-    "description": "Adds .caseless for Lucene queries. Keeps each field's existing keyword type."
-  },
-  "template": {
-    "mappings": {
-      "properties": {
-        "process": {
-          "properties": {
-            "command_line": {
-              "type": "keyword",
-              "ignore_above": 1024,
-              "fields": {
-                "caseless": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "normalizer": "lowercase"
-                }
-              }
-            },
-            "parent": {
-              "properties": {
-                "executable": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "fields": {
-                    "caseless": {
-                      "type": "keyword",
-                      "ignore_above": 1024,
-                      "normalizer": "lowercase"
-                    }
-                  }
-                },
-                "name": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "fields": {
-                    "caseless": {
-                      "type": "keyword",
-                      "ignore_above": 1024,
-                      "normalizer": "lowercase"
-                    }
-                  }
-                },
-                "command_line": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "fields": {
-                    "caseless": {
-                      "type": "keyword",
-                      "ignore_above": 1024,
-                      "normalizer": "lowercase"
-                    }
-                  }
-                }
-              }
-            }
-          }
-        },
-        "file": {
-          "properties": {
-            "path": {
-              "type": "keyword",
-              "ignore_above": 1024,
-              "fields": {
-                "caseless": {
-                  "type": "keyword",
-                  "ignore_above": 1024,
-                  "normalizer": "lowercase"
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  }
-}

salt/elasticsearch/templates/component/so/detection-mappings.json

@@ -154,20 +154,6 @@
             }
           }
         }
-      },
-      "runtime": {
-        "so_detection.sigmaKind": {
-          "type": "keyword",
-          "script": {
-            "source": "if (doc['so_detection.language'].size() == 0 || doc['so_detection.language'].value != 'sigma') { return; } def d = params._source.so_detection; if (d == null || d.content == null) { return; } String c = d.content; String NL = String.valueOf((char) 10); emit(c.startsWith('correlation:') || c.contains(NL + 'correlation:') ? 'correlation' : 'single');"
-          }
-        },
-        "so_detection.sigmaCorrelationType": {
-          "type": "keyword",
-          "script": {
-            "source": "if (doc['so_detection.language'].size() == 0 || doc['so_detection.language'].value != 'sigma') { return; } def d = params._source.so_detection; if (d == null || d.content == null) { return; } String c = d.content; String NL = String.valueOf((char) 10); int i = c.startsWith('correlation:') ? 0 : c.indexOf(NL + 'correlation:'); if (i < 0) { return; } i = c.indexOf(NL, i + 1); while (i >= 0 && i + 1 < c.length()) { int e = c.indexOf(NL, i + 1); String line = e < 0 ? c.substring(i + 1) : c.substring(i + 1, e); if (line.length() > 0 && !Character.isWhitespace(line.charAt(0)) && line.charAt(0) != (char) 35) { return; } String t = line.trim(); if (t.startsWith('type:')) { String v = t.substring(5).trim(); int h = v.indexOf(' ' + String.valueOf((char) 35)); if (h >= 0) { v = v.substring(0, h).trim(); } if (v.length() > 1 && (v.charAt(0) == (char) 39 || v.charAt(0) == (char) 34)) { v = v.substring(1, v.length() - 1); } emit(v); return; } i = e; }"
-          }
-        }
       }
     }
   },

salt/elasticsearch/templates/component/so/detections-alerts-mappings.json

@@ -1,149 +0,0 @@
-{
-  "template": {
-    "mappings": {
-      "properties": {
-        "tags": {
-          "ignore_above": 1024,
-          "type": "keyword"
-        },
-        "sigma_level": {
-          "ignore_above": 1024,
-          "type": "keyword"
-        },
-        "rule": {
-          "properties": {
-            "name": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "uuid": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "category": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "product": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "service": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "correlation": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            }
-          }
-        },
-        "event": {
-          "properties": {
-            "severity": {
-              "type": "long"
-            },
-            "severity_label": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "module": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "dataset": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "kind": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "reason": {
-              "type": "match_only_text",
-              "fields": {
-                "keyword": {
-                  "ignore_above": 1024,
-                  "type": "keyword"
-                }
-              }
-            },
-            "original": {
-              "type": "keyword",
-              "index": false,
-              "doc_values": false
-            }
-          }
-        },
-        "event_data": {
-          "properties": {
-            "@timestamp": {
-              "type": "date"
-            },
-            "window_start": {
-              "type": "date"
-            },
-            "event_count": {
-              "type": "long"
-            },
-            "value_count": {
-              "type": "long"
-            },
-            "event_type_count": {
-              "type": "long"
-            },
-            "value_sum": {
-              "type": "double"
-            },
-            "value_avg": {
-              "type": "double"
-            },
-            "value_percentile": {
-              "type": "double"
-            },
-            "value_median": {
-              "type": "double"
-            }
-          }
-        },
-        "labels": {
-          "properties": {
-            "correlation_group_by": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "correlation_group": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            }
-          }
-        },
-        "related": {
-          "properties": {
-            "ip": {
-              "type": "ip"
-            },
-            "user": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            },
-            "hosts": {
-              "ignore_above": 1024,
-              "type": "keyword"
-            }
-          }
-        },
-        "error": {
-          "properties": {
-            "message": {
-              "type": "match_only_text"
-            }
-          }
-        }
-      }
-    }
-  },
-  "_meta": {
-    "description": "Fields written by the ElastAlert SecurityOnionESAlerter to logs-detections.alerts-so"
-  }
-}

salt/elasticsearch/tools/sbin_jinja/so-catrust

@@ -0,0 +1,26 @@
+#!/bin/bash
+#
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at 
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+. /usr/sbin/so-common
+get_elastic_agent_vars
+
+# Exit on errors, since all lines must succeed
+set -e
+
+# Check to see if we have extracted the ca cert.
+if [ ! -f /opt/so/saltstack/local/salt/elasticsearch/cacerts ]; then
+    docker run -v /etc/pki/ca.crt:/etc/ssl/ca.crt --name so-elasticsearchca --user root --entrypoint jdk/bin/keytool {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elasticsearch:$ELASTIC_AGENT_TARBALL_VERSION -keystore /usr/share/elasticsearch/jdk/lib/security/cacerts -alias SOSCA -import -file /etc/ssl/ca.crt -storepass changeit -noprompt
+    # Make sure symbolic links are followed when copying from container
+    docker cp -L so-elasticsearchca:/usr/share/elasticsearch/jdk/lib/security/cacerts /opt/so/saltstack/local/salt/elasticsearch/cacerts
+    docker cp -L so-elasticsearchca:/etc/pki/ca-trust/extracted/pem/tls-ca-bundle.pem /opt/so/saltstack/local/salt/elasticsearch/tls-ca-bundle.pem
+    docker rm so-elasticsearchca
+    echo "" >> /opt/so/saltstack/local/salt/elasticsearch/tls-ca-bundle.pem
+    echo "sosca" >> /opt/so/saltstack/local/salt/elasticsearch/tls-ca-bundle.pem
+    cat /etc/pki/ca.crt >> /opt/so/saltstack/local/salt/elasticsearch/tls-ca-bundle.pem
+else
+    exit 0
+fi

salt/elasticsearch/tools/sbin_jinja/so-elasticsearch-ilm-policy-load

@@ -7,17 +7,11 @@
 . /usr/sbin/so-common
 
 MAX_JOBS=${MAX_ILM_JOBS:-10}
-ILM_STATEFILE=/opt/so/state/esilm.txt
-rm -f "$ILM_STATEFILE"
 
-check_elasticsearch_responsive
-
-ILM_TMP_DIR=$(mktemp -d)
-trap 'rm -rf "$ILM_TMP_DIR"' EXIT
 # Lock used to serialize block writes so concurrent jobs never interleave their output.
-ILM_OUTPUT_LOCK="$ILM_TMP_DIR/output.lock"
-ILM_FAIL_FILE="$ILM_TMP_DIR/failed"
-touch "$ILM_FAIL_FILE"
+ILM_OUTPUT_LOCK=$(mktemp)
+ILM_FAIL_FILE=$(mktemp)
+trap 'rm -f "$ILM_OUTPUT_LOCK" "$ILM_FAIL_FILE"' EXIT
 
 # Policies are loaded concurrently (up to MAX_JOBS at a time) for speed. Each policy's block is
 # printed the moment its curl returns, so output appears in COMPLETION ORDER, not the order
@@ -26,30 +20,13 @@ echo "Loading ILM policies concurrently; output below appears in completion orde
 echo
 
 put_policy() {
-  local desc="$1" policyname="$2" data="$3" rc=1 attempt out http_code body result reason tmpdata
-  tmpdata=$(mktemp "$ILM_TMP_DIR/${policyname}.XXXXXX.json")
-  printf '%s' "$data" >"$tmpdata"
-
-  for attempt in 1 2 3; do
-    out=$(so-elasticsearch-query "_ilm/policy/${policyname}" -d@"${tmpdata}" -XPUT -w '\n%{http_code}' 2>/dev/null)
-    http_code=${out##*$'\n'} body=${out%$'\n'*}
-
-    if [[ "$http_code" == 200 ]] && jq -e '.acknowledged == true' <<<"$body" >/dev/null 2>&1; then
-      rc=0
-      break
-    fi
-    # 429 = ES rejected/throttled (may succeed later); other 4xx will not
-    [[ "$http_code" == 4?? && "$http_code" != 429 ]] && break
-    (( attempt < 3 )) && sleep 3
-  done
-
-  if (( rc == 0 )); then
-    result='{"acknowledged":true}'
-  else
-    result=${body:-"HTTP ${http_code:-000}"}
-    # flatten tabs/newlines so the TAB fail-file stays one record
-    reason=$(jq -r '(if (.error|type) == "object" then (.error.reason // .error.type) elif (.error|type) == "string" then .error else empty end) // empty | tostring | gsub("[\t\r\n]+"; " ")' <<<"$body" 2>/dev/null)
-    reason="HTTP ${http_code:-000}${reason:+: ${reason}}"
+  local desc="$1" policyname="$2" data="$3" result rc=0
+  if ! result=$(curl -K /opt/so/conf/elasticsearch/curl.config -s -k -L --fail \
+    -X PUT "https://localhost:9200/_ilm/policy/${policyname}" \
+    -H 'Content-Type: application/json' -d"${data}" 2>&1); then
+    rc=1
+  elif ! jq -e '.acknowledged == true' <<<"$result" >/dev/null 2>&1; then
+    rc=1
   fi
 
   # curl above ran in parallel; serialize just this block write so concurrent jobs never interleave.
@@ -57,7 +34,7 @@ put_policy() {
     flock 200
     printf 'Setting up %s policy...\n%s\n\n' "${desc}" "${result}"
     if (( rc != 0 )); then
-      printf '%s\t%s\n' "${policyname}" "${reason}" >>"$ILM_FAIL_FILE"
+      printf '%s\n' "${policyname}" >>"$ILM_FAIL_FILE"
     fi
   } 200>>"${ILM_OUTPUT_LOCK}"
 
@@ -105,15 +82,10 @@ wait || true
 
 if [[ -s "$ILM_FAIL_FILE" ]]; then
   echo "ERROR: Failed to load ILM policy(s):"
-  while IFS=$'\t' read -r POLICY REASON; do
-    if [[ -n "$REASON" ]]; then
-      echo " - ${POLICY}: ${REASON}"
-    else
-      echo " - ${POLICY}"
-    fi
+  while read -r POLICY; do
+    echo " - $POLICY"
   done < "$ILM_FAIL_FILE"
   exit 1
 else
   echo "Successfully loaded all ILM policies."
-  touch "$ILM_STATEFILE"
 fi

salt/firewall/iptables.jinja

@@ -4,19 +4,11 @@
 {%- set role = GLOBALS.role.split('-')[1] %}
 {%- from 'firewall/containers.map.jinja' import NODE_CONTAINERS %}
 
-{%- set NODE_NETWORKS = [] %}
-{%- for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
-{%-   if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
-{%-     do NODE_NETWORKS.append(NETNAME) %}
-{%-   endif %}
-{%- endfor %}
-
 {%- set PR = [] %}
 {%- set D1 = [] %}
 {%- set D2 = [] %}
 {%- for container in NODE_CONTAINERS %}
 {%-   set IP = DOCKERMERGED.containers[container].ip %}
-{%-   set BRIDGE = DOCKERMERGED.containers[container].network %}
 {%-   if DOCKERMERGED.containers[container].port_bindings is defined %}
 {%-     for binding in DOCKERMERGED.containers[container].port_bindings %}
 {#-       cant split int so we convert to string #}
@@ -43,11 +35,11 @@
 {%-         endif %}
 {%-         do PR.append("-A POSTROUTING -s " ~ DOCKERMERGED.containers[container].ip ~ "/32 -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 -p " ~  proto ~ " -m " ~ proto  ~ " --dport " ~ containerPort ~ " -j MASQUERADE") %}
 {%-         if bindip | length and bindip != '0.0.0.0' %}
-{%-           do D1.append("-A DOCKER -d " ~ bindip ~ "/32 ! -i " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
+{%-           do D1.append("-A DOCKER -d " ~ bindip ~ "/32 ! -i sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
 {%-         else %}
-{%-           do D1.append("-A DOCKER ! -i " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
+{%-           do D1.append("-A DOCKER ! -i sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
 {%-         endif %}
-{%-         do D2.append("-A DOCKER -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 ! -i " ~ BRIDGE ~ " -o " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ containerPort ~ " -j ACCEPT") %}
+{%-         do D2.append("-A DOCKER -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 ! -i sobridge -o sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ containerPort ~ " -j ACCEPT") %}
 {%-     endfor %}
 {%-   endif %}
 {%- endfor %}
@@ -60,15 +52,11 @@
 :DOCKER - [0:0]
 -A PREROUTING -m addrtype --dst-type LOCAL -j DOCKER
 -A OUTPUT ! -d 127.0.0.0/8 -m addrtype --dst-type LOCAL -j DOCKER
-{%- for NETNAME in NODE_NETWORKS %}
--A POSTROUTING -s {{ DOCKERMERGED.networks[NETNAME].range }} ! -o {{ NETNAME }} -j MASQUERADE
-{%- endfor %}
+-A POSTROUTING -s {{DOCKERMERGED.range}} ! -o sobridge -j MASQUERADE
 {%- for rule in PR %}
 {{ rule }}
 {%- endfor %}
-{%- for NETNAME in NODE_NETWORKS %}
--A DOCKER -i {{ NETNAME }} -j RETURN
-{%- endfor %}
+-A DOCKER -i sobridge -j RETURN
 {%- for rule in D1 %}
 {{ rule }}
 {%- endfor %}
@@ -109,12 +97,10 @@ COMMIT
 {%- endif %}
 -A FORWARD -j DOCKER-USER
 -A FORWARD -j DOCKER-ISOLATION-STAGE-1
-{%- for NETNAME in NODE_NETWORKS %}
--A FORWARD -o {{ NETNAME }} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A FORWARD -o {{ NETNAME }} -j DOCKER
--A FORWARD -i {{ NETNAME }} ! -o {{ NETNAME }} -j ACCEPT
--A FORWARD -i {{ NETNAME }} -o {{ NETNAME }} -j ACCEPT
-{%- endfor %}
+-A FORWARD -o sobridge -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
+-A FORWARD -o sobridge -j DOCKER
+-A FORWARD -i sobridge ! -o sobridge -j ACCEPT
+-A FORWARD -i sobridge -o sobridge -j ACCEPT
 -A FORWARD -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
 -A FORWARD -i lo -j ACCEPT
 -A FORWARD -m conntrack --ctstate INVALID -j DROP
@@ -126,18 +112,13 @@ COMMIT
 {%- for rule in D2 %}
 {{ rule }}
 {%- endfor %}
-{% for NETNAME in NODE_NETWORKS %}
--A DOCKER-ISOLATION-STAGE-1 -i {{ NETNAME }} ! -o {{ NETNAME }} -j DOCKER-ISOLATION-STAGE-2
-{%- endfor %}
+
+-A DOCKER-ISOLATION-STAGE-1 -i sobridge ! -o sobridge -j DOCKER-ISOLATION-STAGE-2
 -A DOCKER-ISOLATION-STAGE-1 -j RETURN
-{%- for NETNAME in NODE_NETWORKS %}
--A DOCKER-ISOLATION-STAGE-2 -o {{ NETNAME }} -j DROP
-{%- endfor %}
+-A DOCKER-ISOLATION-STAGE-2 -o sobridge -j DROP
 -A DOCKER-ISOLATION-STAGE-2 -j RETURN
-{%- for NETNAME in NODE_NETWORKS %}
--A DOCKER-USER ! -i {{ NETNAME }} -o {{ NETNAME }} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-USER ! -i {{ NETNAME }} -o {{ NETNAME }} -j LOGGING
-{%- endfor %}
+-A DOCKER-USER ! -i sobridge -o sobridge -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
+-A DOCKER-USER ! -i sobridge -o sobridge -j LOGGING
 -A DOCKER-USER -j RETURN
 -A LOGGING -m limit --limit 2/min -j LOG --log-prefix "IPTables-dropped: "
 -A LOGGING -j DROP

salt/firewall/map.jinja

@@ -4,12 +4,8 @@
 
 {# add our ip to self #}
 {% do FIREWALL_DEFAULT.firewall.hostgroups.self.append(GLOBALS.node_ip) %}
-{# add dockernet ranges #}
-{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
-{%   if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
-{%     do FIREWALL_DEFAULT.firewall.hostgroups.dockernet.append(NETWORK.range) %}
-{%   endif %}
-{% endfor %}
+{# add dockernet range #}
+{% do FIREWALL_DEFAULT.firewall.hostgroups.dockernet.append(DOCKERMERGED.range) %}
 
 {% if GLOBALS.role == 'so-idh' %}
 {%   from 'idh/opencanary_config.map.jinja' import IDH_PORTGROUPS %}

salt/hydra/enabled.sls

@@ -13,11 +13,9 @@
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   if 'api' in salt['pillar.get']('features', []) %}
 
 include:
-  - ca.trust
   - hydra.config
   - hydra.sostatus
 
@@ -28,10 +26,9 @@ so-hydra:
     - hostname: hydra
     - name: so-hydra
     - networks:
-      - soauth:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-hydra'].ips['soauth'] }}
+      - sobridge:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-hydra'].ip }}
     - binds:
-      - {{ CATRUST.dir }}
       - /opt/so/conf/hydra/:/hydra-conf:ro
       - /opt/so/log/hydra/:/hydra-log:rw
       - /nsm/hydra/db:/hydra-data:rw
@@ -63,7 +60,6 @@ so-hydra:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: hydraconfig
     - require:
       - file: hydraconfig
@@ -77,7 +73,7 @@ delete_so-hydra_so-status.disabled:
 
 wait_for_hydra:
   http.wait_for_successful_query:
-    - name: 'http://{{ DOCKERMERGED.containers['so-hydra'].ips['soauth'] }}:4444/health/alive'
+    - name: 'http://{{ GLOBALS.manager }}:4444/health/alive'
     - ssl: True
     - verify_ssl: False
     - status:

salt/hypervisor/init.sls

@@ -21,16 +21,12 @@ hypervisor_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://hypervisor/tools/sbin
-    - user: root
-    - group: root
     - file_mode: 744
 
 hypervisor_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://hypervisor/tools/sbin_jinja
-    - user: root
-    - group: root
     - template: jinja
     - file_mode: 744
 

salt/idh/config.sls

@@ -86,8 +86,8 @@ idh_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://idh/tools/sbin
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939
     - file_mode: 755
 
 #idh_sbin_jinja:

salt/idh/enabled.sls

@@ -6,11 +6,9 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 
 include:
-  - ca.trust
   - idh.config
   - idh.sostatus
 
@@ -22,7 +20,6 @@ so-idh:
     - detach: True
     - network_mode: host
     - binds:
-      - {{ CATRUST.dir }}
       - /nsm/idh:/var/tmp:rw
       - /opt/so/conf/idh/http-skins:/opt/opencanary/http-skins:ro
       - /opt/so/conf/idh/opencanary.conf:/etc/opencanaryd/opencanary.conf:ro
@@ -37,13 +34,12 @@ so-idh:
       - {{ XTRAHOST }}
       {% endfor %}
     {% endif %}
+    {% if DOCKERMERGED.containers['so-idh'].extra_env %}
     - environment:
-      - REQUESTS_CA_BUNDLE=/etc/pki/tls/certs/ca-bundle.crt
-      {% if DOCKERMERGED.containers['so-idh'].extra_env %}
-        {% for XTRAENV in DOCKERMERGED.containers['so-idh'].extra_env %}
+      {% for XTRAENV in DOCKERMERGED.containers['so-idh'].extra_env %}
       - {{ XTRAENV }}
-        {% endfor %}
-      {% endif %}
+      {% endfor %}
+    {% endif %}
     {% if DOCKERMERGED.containers['so-idh'].ulimits %}
     - ulimits:
     {%   for ULIMIT in DOCKERMERGED.containers['so-idh'].ulimits %}
@@ -51,7 +47,6 @@ so-idh:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: opencanary_config
     - require:
       - file: opencanary_config

salt/influxdb/config.sls

@@ -41,8 +41,8 @@ influxdb_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://influxdb/tools/sbin
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939
     - file_mode: 755
 
 #influxdb_sbin_jinja:

salt/influxdb/enabled.sls

@@ -6,13 +6,11 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   set PASSWORD = salt['pillar.get']('secrets:influx_pass') %}
 {%   set TOKEN = salt['pillar.get']('influxdb:token') %}
 
 include:
-  - ca.trust
   - influxdb.ssl
   - influxdb.config
   - influxdb.sostatus
@@ -40,7 +38,6 @@ so-influxdb:
         {% endfor %}
       {% endif %}
     - binds:
-      - {{ CATRUST.pem }}:/etc/ssl/certs/ca-certificates.crt:ro
       - /opt/so/log/influxdb/:/log:rw
       - /opt/so/conf/influxdb/config.yaml:/conf/config.yaml:ro
       - /opt/so/conf/influxdb/etc:/etc/influxdb2:rw
@@ -69,7 +66,6 @@ so-influxdb:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: influxdbconf
       - x509: influxdb_key
       - x509: influxdb_crt
@@ -98,11 +94,9 @@ metrics_link_file:
       - docker_container: so-influxdb
 
 # Install cron job to determine size of influxdb for telegraf
-# telegraf reads this while the cron rewrites it, so write aside and rename rather than
-# truncating in place. tgraflogdir recurses ownership, so the temp file is chowned to match
 get_influxdb_size:
   cron.present:
-    - name: 'du -s -k /nsm/influxdb | cut -f1 > /opt/so/log/telegraf/influxdb_size.log.tmp 2>&1; chown 939:939 /opt/so/log/telegraf/influxdb_size.log.tmp; mv -f /opt/so/log/telegraf/influxdb_size.log.tmp /opt/so/log/telegraf/influxdb_size.log'
+    - name: 'du -s -k /nsm/influxdb | cut -f1 > /opt/so/log/telegraf/influxdb_size.log 2>&1'
     - identifier: get_influxdb_size
     - user: root
     - minute: '*/1'

salt/kafka/config.sls

@@ -21,7 +21,6 @@ kafka_user:
     - gid: 960
     - home: /opt/so/conf/kafka
     - createhome: False
-    - shell: /sbin/nologin
 
 kafka_home_dir:
   file.absent:
@@ -31,16 +30,16 @@ kafka_sbin_tools:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kafka/tools/sbin
-    - user: root
-    - group: root
+    - user: 960
+    - group: 960
     - file_mode: 755
 
 kafka_sbin_jinja_tools:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kafka/tools/sbin_jinja
-    - user: root
-    - group: root
+    - user: 960
+    - group: 960
     - file_mode: 755
     - template: jinja
     - defaults:

salt/kafka/enabled.sls

@@ -12,14 +12,12 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   set KAFKANODES = salt['pillar.get']('kafka:nodes') %}
 {%   set KAFKA_EXTERNAL_ACCESS = salt['pillar.get']('kafka:config:external_access:enabled', default=False) %}
 {%   if 'gmd' in salt['pillar.get']('features', []) %}
 
 include:
-  - ca.trust
   - kafka.ca
   - kafka.config
   - kafka.ssl
@@ -53,7 +51,6 @@ so-kafka:
       - {{ BINDING }}
       {% endfor %}
     - binds:
-      - {{ CATRUST.java }}:/opt/java/openjdk/lib/security/cacerts:ro
       - /etc/pki/kafka.p12:/etc/pki/kafka.p12:ro
       - /opt/so/conf/kafka/kafka-truststore.jks:/etc/pki/kafka-truststore.jks:ro
       - /nsm/kafka/data/:/nsm/kafka/data/:rw
@@ -64,11 +61,6 @@ so-kafka:
       {% if KAFKA_EXTERNAL_ACCESS %}
       - /opt/so/conf/kafka/kafka_server_jaas.conf:/opt/kafka/config/kafka_server_jaas.conf:ro
       {% endif %}
-      {% if DOCKERMERGED.containers['so-kafka'].custom_bind_mounts %}
-        {% for BIND in DOCKERMERGED.containers['so-kafka'].custom_bind_mounts %}
-      - {{ BIND }}
-        {% endfor %}
-      {% endif %}
     {% if DOCKERMERGED.containers['so-kafka'].ulimits %}
     - ulimits:
     {%   for ULIMIT in DOCKERMERGED.containers['so-kafka'].ulimits %}
@@ -76,7 +68,6 @@ so-kafka:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       {% for sc in ['server', 'client'] %}
       - file: kafka_kraft_{{sc}}_properties
       {% endfor %}

salt/kibana/config.sls

@@ -22,7 +22,6 @@ kibana:
     - gid: 932
     - home: /opt/so/conf/kibana
     - createhome: False
-    - shell: /sbin/nologin
 
 # Drop the correct nginx config based on role
 
@@ -37,16 +36,16 @@ kibana_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kibana/tools/sbin
-    - user: root
-    - group: root
+    - user: 932
+    - group: 939
     - file_mode: 755
 
 kibana_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kibana/tools/sbin_jinja
-    - user: root
-    - group: root
+    - user: 932
+    - group: 939 
     - file_mode: 755
     - template: jinja
     - defaults:

salt/kibana/defaults.yaml

@@ -22,7 +22,7 @@ kibana:
           - default
           - file
     migrations:
-      discardCorruptObjects: "9.4.8"
+      discardCorruptObjects: "9.4.5"
     telemetry:
       enabled: False
     xpack:

salt/kibana/enabled.sls

@@ -8,10 +8,8 @@
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 
 include:
-  - ca.trust
   - kibana.config
   - kibana.sostatus
 
@@ -29,7 +27,6 @@ so-kibana:
       - ELASTICSEARCH_HOST={{ GLOBALS.manager }}
       - ELASTICSEARCH_PORT=9200
       - MANAGER={{ GLOBALS.manager }}
-      - NODE_OPTIONS=--use-openssl-ca
       {% if DOCKERMERGED.containers['so-kibana'].extra_env %}
         {% for XTRAENV in DOCKERMERGED.containers['so-kibana'].extra_env %}
       - {{ XTRAENV }}
@@ -43,7 +40,6 @@ so-kibana:
       {% endfor %}
     {% endif %}
     - binds:
-      - {{ CATRUST.dir }}
       - /opt/so/conf/kibana/etc:/usr/share/kibana/config:rw
       - /opt/so/log/kibana:/var/log/kibana:rw
       - /opt/so/conf/kibana/customdashboards:/usr/share/kibana/custdashboards:ro
@@ -64,7 +60,6 @@ so-kibana:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: kibanaconfig
 
 wait_for_so-kibana:

salt/kratos/config.sls

@@ -27,7 +27,6 @@ kratos:
     - uid: 928
     - gid: 928
     - home: /opt/so/conf/kratos
-    - shell: /sbin/nologin
 
 kratosdir:
   file.directory:

salt/kratos/enabled.sls

@@ -7,10 +7,8 @@
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 
 include:
-  - ca.trust
   - kratos.config
   - kratos.sostatus
 
@@ -21,10 +19,9 @@ so-kratos:
     - hostname: kratos
     - name: so-kratos
     - networks:
-      - soauth:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-kratos'].ips['soauth'] }}
+      - sobridge:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-kratos'].ip }}
     - binds:
-      - {{ CATRUST.dir }}
       - /opt/so/conf/kratos/:/kratos-conf:ro
       - /opt/so/log/kratos/:/kratos-log:rw
       - /nsm/kratos/db:/kratos-data:rw
@@ -56,7 +53,6 @@ so-kratos:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: kratosschema
       - file: kratosconfig
     - require:
@@ -75,7 +71,7 @@ delete_so-kratos_so-status.disabled:
 
 wait_for_kratos:
   http.wait_for_successful_query:
-    - name: 'http://{{ DOCKERMERGED.containers['so-kratos'].ips['soauth'] }}:4434/'
+    - name: 'http://{{ GLOBALS.manager }}:4434/'
     - ssl: True
     - verify_ssl: False
     - status:

salt/libvirt/64962/init.sls

@@ -6,8 +6,6 @@ so-fix-salt-ldap_script:
   file.managed:
     - name: /usr/sbin/so-fix-salt-ldap.py
     - source: salt://libvirt/64962/scripts/so-fix-salt-ldap.py
-    - user: root
-    - group: root
     - mode: 744
 
 fix-salt-ldap:

salt/logstash/config.sls

@@ -35,14 +35,13 @@ logstash:
     - uid: 931
     - gid: 931
     - home: /opt/so/conf/logstash
-    - shell: /sbin/nologin
 
 logstash_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://logstash/tools/sbin
-    - user: root
-    - group: root
+    - user: 931
+    - group: 939
     - file_mode: 755
 
 #logstash_sbin_jinja:

salt/logstash/enabled.sls

@@ -6,7 +6,6 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   from 'logstash/map.jinja' import LOGSTASH_MERGED %}
 {%   from 'logstash/map.jinja' import LOGSTASH_NODES %}
@@ -14,6 +13,9 @@
 
 include:
   - ca
+{%   if GLOBALS.role not in ['so-receiver','so-fleet'] %}
+  - elasticsearch.ca
+{%   endif %}
 {# Kafka ca runs on nodes that can run logstash for Kafka input / output. Only when Kafka is global pipeline #}
 {%   if GLOBALS.role in ['so-searchnode', 'so-manager', 'so-managerhype', 'so-managersearch', 'so-receiver', 'so-standalone'] and GLOBALS.pipeline == 'KAFKA' %}
   - kafka.ca
@@ -56,8 +58,6 @@ so-logstash:
       - {{ BINDING }}
       {% endfor %}
     - binds:
-      - {{ CATRUST.dir }}
-      - {{ CATRUST.java }}:/usr/share/logstash/jdk/lib/security/cacerts:ro
       - /opt/so/conf/elasticsearch/templates/:/templates/:ro
       - /opt/so/conf/logstash/etc/:/usr/share/logstash/config/:ro
       - /opt/so/conf/logstash/pipelines:/usr/share/logstash/pipelines:ro
@@ -78,6 +78,10 @@ so-logstash:
       - /etc/pki/filebeat.p8:/usr/share/logstash/filebeat.key:ro
           {% endif %}
       {% endif %}
+      {% if GLOBALS.role not in ['so-receiver','so-fleet'] %}
+      - /opt/so/conf/ca/cacerts:/etc/pki/ca-trust/extracted/java/cacerts:ro
+      - /opt/so/conf/ca/tls-ca-bundle.pem:/etc/pki/ca-trust/extracted/pem/tls-ca-bundle.pem:ro
+      {% endif %}
       {% if GLOBALS.pipeline == "KAFKA" and GLOBALS.role in ['so-manager', 'so-managerhype', 'so-managersearch', 'so-standalone', 'so-searchnode'] %}
       - /etc/pki/kafka-logstash.p12:/usr/share/logstash/kafka-logstash.p12:ro
       - /opt/so/conf/kafka/kafka-truststore.jks:/etc/pki/kafka-truststore.jks:ro
@@ -100,11 +104,14 @@ so-logstash:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: lsetcsync
       - file: lslog4j2
       - file: lspipelinesyml
       - file: trusttheca
+      {% if GLOBALS.is_manager %}
+      - file: elasticsearch_cacerts
+      - file: elasticsearch_capems
+      {% endif %}
       {% if GLOBALS.is_manager or GLOBALS.role in ['so-fleet', 'so-heavynode', 'so-receiver'] %}
       - x509: etc_elasticfleet_logstash_crt
       - x509: etc_elasticfleet_logstash_key
@@ -126,6 +133,10 @@ so-logstash:
       {% endif %}
     - require:
       - file: trusttheca
+      {% if GLOBALS.is_manager %}
+      - file: elasticsearch_cacerts
+      - file: elasticsearch_capems
+      {% endif %}
       {% if GLOBALS.is_manager or GLOBALS.role in ['so-fleet', 'so-heavynode', 'so-receiver'] %}
       - x509: etc_elasticfleet_logstash_crt
       - x509: etc_elasticfleet_logstash_key

salt/manager/init.sls

@@ -113,8 +113,8 @@ manager_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://manager/tools/sbin
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939
     - file_mode: 755
     - exclude_pat:
       - "*_test.py"
@@ -124,8 +124,8 @@ manager_sbin_jinja:
   file.recurse:
     - name: /usr/sbin/
     - source: salt://manager/tools/sbin_jinja/
-    - user: root
-    - group: root
+    - user: socore
+    - group: socore
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -166,7 +166,7 @@ so-repo-sync:
 
 so_fleetagent_status:
   cron.present:
-    - name: '/usr/sbin/so-elasticagent-status > /opt/so/log/agents/agentstatus.log.tmp 2>&1; mv -f /opt/so/log/agents/agentstatus.log.tmp /opt/so/log/agents/agentstatus.log'
+    - name: /usr/sbin/so-elasticagent-status > /opt/so/log/agents/agentstatus.log 2>&1
     - identifier: so_fleetagent_status
     - user: root
     - minute: '*/5'
@@ -190,15 +190,11 @@ so_fleetagent_monitor:
   - month: '*'
   - dayweek: '*'
 
-# This tree is the source of every root-executed script (/usr/sbin, reactors, _runners,
-# engines, salt-relay.sh). SOC mounts /opt/so/saltstack rw as uid 939 but only writes
-# under local/. Do not add dir_mode/file_mode here -- SOC reads default/ and 750/640
-# would break its config load.
-root_own_saltstack_default:
+socore_own_saltstack_default:
   file.directory:
     - name: /opt/so/saltstack/default
-    - user: root
-    - group: root
+    - user: socore
+    - group: socore
     - recurse:
       - user
       - group

salt/manager/tools/sbin/so-client

@@ -106,8 +106,7 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-hydraContainer=${HYDRA_CONTAINER:-so-hydra}
-hydraUrl=${HYDRA_URL:-http://localhost:4445}
+hydraUrl=${HYDRA_URL:-http://127.0.0.1:4445}
 socRolesFile=${SOC_ROLES_FILE:-/opt/so/conf/soc/soc_clients_roles}
 soUID=${SOCORE_UID:-939}
 soGID=${SOCORE_GID:-939}
@@ -125,10 +124,6 @@ function fail() {
   exit 1
 }
 
-function hydraCurl() {
-  docker exec "$hydraContainer" curl "$@"
-}
-
 function require() {
   cmd=$1
   which "$1" 2>&1 > /dev/null
@@ -138,8 +133,8 @@ function require() {
 # Verify this environment is capable of running this script
 function verifyEnvironment() {
   require "jq"
-  require "docker"
-  response=$(hydraCurl -Ss -L ${hydraUrl}/health/alive)
+  require "curl"
+  response=$(curl -Ss -L ${hydraUrl}/health/alive)
   [[ "$response" != '{"status":"ok"}' ]] && fail "Unable to communicate with Hydra; specify URL via HYDRA_URL environment variable"
 }
 
@@ -169,7 +164,7 @@ function ensureRoleFileExists() {
 }
 
 function listClients() {
-  response=$(hydraCurl -Ss -L -f ${hydraUrl}/admin/clients)
+  response=$(curl -Ss -L -f ${hydraUrl}/admin/clients)
   [[ $? != 0 ]] && fail "Unable to communicate with Hydra"
 
   clientIds=$(echo "${response}" | jq -r ".[] | .client_id" | sort)
@@ -256,7 +251,7 @@ function createClient() {
 EOF
   )
   
-  response=$(hydraCurl -Ss -L --fail-with-body -X POST ${hydraUrl}/admin/clients -d "$body")
+  response=$(curl -Ss -L --fail-with-body -X POST ${hydraUrl}/admin/clients -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -288,7 +283,7 @@ function update() {
 EOF
   )
   
-  response=$(hydraCurl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
+  response=$(curl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -310,7 +305,7 @@ function generateSecret() {
 EOF
   )
   
-  response=$(hydraCurl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
+  response=$(curl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -322,7 +317,7 @@ function deleteClient() {
 
   [[ ${identityId} == "" ]] && fail "Client not found"
 
-  response=$(hydraCurl -Ss -XDELETE -L --fail-with-body "${hydraUrl}/admin/clients/$identityId")
+  response=$(curl -Ss -XDELETE -L --fail-with-body "${hydraUrl}/admin/clients/$identityId")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"

salt/manager/tools/sbin/so-minion

@@ -121,14 +121,8 @@ for i in "$@"; do
 	esac
 done
 
-if [[ -n "$MINION_ID" && ! "$MINION_ID" =~ ^[A-Za-z0-9._-]{1,253}$ ]]; then
-	echo "Invalid minion id: $MINION_ID"
-	log "ERROR" "Invalid minion id: $MINION_ID"
-	exit 1
-fi
-
-readonly PILLARFILE=/opt/so/saltstack/local/pillar/minions/$MINION_ID.sls
-readonly ADVPILLARFILE=/opt/so/saltstack/local/pillar/minions/adv_$MINION_ID.sls
+PILLARFILE=/opt/so/saltstack/local/pillar/minions/$MINION_ID.sls
+ADVPILLARFILE=/opt/so/saltstack/local/pillar/minions/adv_$MINION_ID.sls
 
 function getinstallinfo() {
 	log "INFO" "Getting install info for minion $MINION_ID"
@@ -139,23 +133,10 @@ function getinstallinfo() {
 		return 1
 	fi
 
-	# install.txt is controlled by the minion; only accept known keys and never eval or export them
-	local line key
-	while IFS= read -r line; do
-		[[ "$line" == *=* ]] || continue
-		key=${line%%=*}
-		case "$key" in
-			MAINIP|MNIC|NODE_DESCRIPTION|ES_HEAP_SIZE|PATCHSCHEDULENAME|INTERFACE|NODETYPE|CORECOUNT|LSHOSTNAME|LSHEAP|CPUCORES|IDH_MGTRESTRICT|IDH_SERVICES)
-				printf -v "$key" '%s' "${line#*=}"
-				;;
-			*)
-				log "WARN" "Ignoring unexpected install var from $MINION_ID: ${key:0:64}"
-				;;
-		esac
-	done <<< "$INSTALLVARS"
-
-	if [[ "$NODE_DESCRIPTION" == \'*\' ]]; then
-		NODE_DESCRIPTION=${NODE_DESCRIPTION:1:-1}
+	while read -r var; do export "$var"; done <<< "$INSTALLVARS"
+	if [ $? -ne 0 ]; then
+		log "ERROR" "Failed to source install variables"
+		return 1
 	fi
 
 	log "INFO" "Fetched install info for $MINION_ID (node type: ${NODETYPE:-unset})"
@@ -195,12 +176,6 @@ function pcapspace() {
 		fi
 	fi
 
-	# Must be checked before arithmetic expansion, which evaluates array subscripts
-	if [[ ! "$SPACESIZE" =~ ^[0-9]+$ ]]; then
-		log "ERROR" "Invalid disk size for $MINION_ID: ${SPACESIZE:0:64}"
-		return 1
-	fi
-
 	local s=$(( $SPACESIZE / 1000000 ))
 	local s1=$(( $s / 4 * $PCAP_PERCENTAGE ))
 
@@ -1075,57 +1050,6 @@ function updateMineAndApplyStates() {
 	fi
 }
 
-# Values end up in a Jinja-rendered pillar and in bash, and may come from the minion
-function validate_minion_vars() {
-	local error_msg=""
-	# Inline rather than valid_ip4: so-common is not installed yet when setup runs -o=setup
-	local octet='(25[0-5]|2[0-4][0-9]|1?[0-9]?[0-9])'
-	local ip4_re="^($octet\.){3}$octet$"
-
-	case "$NODETYPE" in
-		EVAL|STANDALONE|MANAGER|MANAGERSEARCH|MANAGERHYPE|IMPORT)
-			# Manager pillars also rewrite the CA pillar, so never accept them from a remote node
-			[[ "$OPERATION" == "setup" ]] || error_msg="Node type $NODETYPE can only be configured during setup"
-			;;
-		FLEET|IDH|HEAVYNODE|SENSOR|SEARCHNODE|RECEIVER|HYPERVISOR|DESKTOP)
-			;;
-		*)
-			error_msg="Invalid node type: ${NODETYPE:0:64}"
-			;;
-	esac
-
-	if [[ -z "$error_msg" ]]; then
-		if [[ ! "$MAINIP" =~ $ip4_re ]]; then
-			error_msg="Invalid MAINIP: ${MAINIP:0:64}"
-		elif [[ ! "$MNIC" =~ ^[A-Za-z0-9._-]*$ ]]; then
-			error_msg="Invalid MNIC: ${MNIC:0:64}"
-		elif [[ ! "$INTERFACE" =~ ^[A-Za-z0-9._-]*$ ]]; then
-			error_msg="Invalid INTERFACE: ${INTERFACE:0:64}"
-		elif [[ ! "$LSHOSTNAME" =~ ^[A-Za-z0-9._-]*$ ]]; then
-			error_msg="Invalid LSHOSTNAME: ${LSHOSTNAME:0:64}"
-		elif [[ ! "$ES_HEAP_SIZE" =~ ^([0-9]+[kKmMgG]?)?$ ]]; then
-			error_msg="Invalid ES_HEAP_SIZE: ${ES_HEAP_SIZE:0:64}"
-		elif [[ ! "$LSHEAP" =~ ^([0-9]+[kKmMgG]?)?$ ]]; then
-			error_msg="Invalid LSHEAP: ${LSHEAP:0:64}"
-		elif [[ ! "$CORECOUNT" =~ ^[0-9]*$ ]]; then
-			error_msg="Invalid CORECOUNT: ${CORECOUNT:0:64}"
-		elif [[ ! "$CPUCORES" =~ ^[0-9]*$ ]]; then
-			error_msg="Invalid CPUCORES: ${CPUCORES:0:64}"
-		elif [[ ! "$IDH_MGTRESTRICT" =~ ^(True|False)?$ ]]; then
-			error_msg="Invalid IDH_MGTRESTRICT: ${IDH_MGTRESTRICT:0:64}"
-		fi
-	fi
-
-	if [[ -n "$error_msg" ]]; then
-		log "ERROR" "$error_msg"
-		echo "$error_msg"
-		return 1
-	fi
-
-	# Free text; removing braces is enough to prevent any Jinja delimiter
-	NODE_DESCRIPTION=${NODE_DESCRIPTION//[\{\}[:cntrl:]]/}
-}
-
 function setupMinionFiles() {
 	log "INFO" "Setting up minion files for $MINION_ID (pillar: $PILLARFILE)"
 	
@@ -1137,8 +1061,6 @@ function setupMinionFiles() {
 		return 1
 	fi
 
-	validate_minion_vars || return 1
-
 	# Create the base minion files
 	create_minion_files || return 1
 

salt/manager/tools/sbin/so-saltstack-update

@@ -124,8 +124,8 @@ copy_new_files() {
   
   rsync -a salt $default_salt_dir/
   rsync -a pillar $default_salt_dir/
-  chown -R root:root $default_salt_dir/salt
-  chown -R root:root $default_salt_dir/pillar
+  chown -R socore:socore $default_salt_dir/salt
+  chown -R socore:socore $default_salt_dir/pillar
   chmod 755 $default_salt_dir/pillar/firewall/addfirewall.sh
 
   rm -rf /tmp/sogh

salt/manager/tools/sbin/so-user

@@ -129,8 +129,7 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-kratosContainer=${KRATOS_CONTAINER:-so-kratos}
-kratosUrl=${KRATOS_URL:-http://localhost:4434/admin}
+kratosUrl=${KRATOS_URL:-http://127.0.0.1:4434/admin}
 databasePath=${KRATOS_DB_PATH:-/nsm/kratos/db/db.sqlite}
 databaseTimeout=${KRATOS_DB_TIMEOUT:-5000}
 bcryptRounds=${BCRYPT_ROUNDS:-12}
@@ -155,10 +154,6 @@ function fail() {
   exit 1
 }
 
-function kratosCurl() {
-  docker exec "$kratosContainer" curl "$@"
-}
-
 function require() {
   cmd=$1
   which "$1" 2>&1 > /dev/null
@@ -169,18 +164,18 @@ function require() {
 function verifyEnvironment() {
   require "htpasswd"
   require "jq"
-  require "docker"
+  require "curl"
   require "openssl"
   require "sqlite3"
   [[ ! -f $databasePath ]] && fail "Unable to find database file; specify path via KRATOS_DB_PATH environment variable"
-  response=$(kratosCurl -Ss -L ${kratosUrl}/)
+  response=$(curl -Ss -L ${kratosUrl}/)
   [[ "$response" != "404 page not found" ]] && fail "Unable to communicate with Kratos; specify URL via KRATOS_URL environment variable"
 }
 
 function findIdByEmail() {
   email=${1,,}
 
-  response=$(kratosCurl -Ss -L ${kratosUrl}/identities)
+  response=$(curl -Ss -L ${kratosUrl}/identities)
   identityId=$(echo "${response}" | jq -r ".[] | select(.verifiable_addresses[0].value == \"$email\") | .id")
   echo $identityId
 }
@@ -421,7 +416,7 @@ function syncAll() {
 }
 
 function listUsers() {
-  response=$(kratosCurl -Ss -L ${kratosUrl}/identities)
+  response=$(curl -Ss -L ${kratosUrl}/identities)
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   users=$(echo "${response}" | jq -r ".[] | .verifiable_addresses[0].value" | sort)
@@ -500,7 +495,7 @@ function createUser() {
 EOF
   )
   
-  response=$(kratosCurl -Ss -L ${kratosUrl}/identities -d "$addUserJson")
+  response=$(curl -Ss -L ${kratosUrl}/identities -d "$addUserJson")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   identityId=$(echo "${response}" | jq -r ".id")
@@ -523,7 +518,7 @@ function updateStatus() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(kratosCurl -Ss -L "${kratosUrl}/identities/$identityId")
+  response=$(curl -Ss -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   schemaId=$(echo "$response" | jq -r .schema_id)
@@ -536,7 +531,7 @@ function updateStatus() {
     state="inactive"
   fi
   body="{ \"schema_id\": \"$schemaId\", \"state\": \"$state\", \"traits\": $traitBlock }"
-  response=$(kratosCurl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
+  response=$(curl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
   [[ $? != 0 ]] && fail "Unable to update user"
 }
 
@@ -555,7 +550,7 @@ function updateUserProfile() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(kratosCurl -Ss -L "${kratosUrl}/identities/$identityId")
+  response=$(curl -Ss -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   schemaId=$(echo "$response" | jq -r .schema_id)
@@ -564,7 +559,7 @@ function updateUserProfile() {
   traitBlock="{\"email\":\"$email\",\"firstName\":\"$firstName\",\"lastName\":\"$lastName\",\"note\":\"$note\"}"
 
   body="{ \"schema_id\": \"$schemaId\", \"state\": \"$state\", \"traits\": $traitBlock }"
-  response=$(kratosCurl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
+  response=$(curl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
   [[ $? != 0 ]] && fail "Unable to update user"
 }
 
@@ -574,7 +569,7 @@ function deleteUser() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(kratosCurl -Ss -XDELETE -L "${kratosUrl}/identities/$identityId")
+  response=$(curl -Ss -XDELETE -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   rolesTmpFile="${socRolesFile}.tmp"

salt/manager/tools/sbin/so-yaml.py

@@ -42,8 +42,7 @@ def loadYaml(filename):
     try:
         with open(filename, "r") as file:
             content = file.read()
-            loaded = yaml.safe_load(content)
-            return loaded if loaded is not None else {}
+            return yaml.safe_load(content)
     except FileNotFoundError:
         print(f"File not found: {filename}", file=sys.stderr)
         sys.exit(1)

salt/manager/tools/sbin/so-yaml_test.py

@@ -95,20 +95,6 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep2: ab\nkey2: false\n"
         self.assertEqual(actual, expected)
 
-    def test_remove_empty_file(self):
-        filename = "/tmp/so-yaml_test-remove-empty.yaml"
-        file = open(filename, "w")
-        file.close()
-
-        code = soyaml.remove([filename, "key1"])
-        self.assertEqual(code, 0)
-
-        file = open(filename, "r")
-        actual = file.read()
-        file.close()
-
-        self.assertEqual(actual, "{}\n")
-
     def test_remove_missing_args(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -308,36 +294,6 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep1: 45\n    deep2: d\nkey2: false\nkey3:\n- e\n- f\n- g\n"
         self.assertEqual(actual, expected)
 
-    def test_add_empty_file(self):
-        filename = "/tmp/so-yaml_test-add-empty.yaml"
-        file = open(filename, "w")
-        file.close()
-
-        code = soyaml.add([filename, "telegraf.output", "BOTH"])
-        self.assertEqual(code, 0)
-
-        file = open(filename, "r")
-        actual = file.read()
-        file.close()
-
-        expected = "telegraf:\n  output: BOTH\n"
-        self.assertEqual(actual, expected)
-
-    def test_add_empty_file_simple(self):
-        filename = "/tmp/so-yaml_test-add-empty-simple.yaml"
-        file = open(filename, "w")
-        file.close()
-
-        code = soyaml.add([filename, "telegraf", "BOTH"])
-        self.assertEqual(code, 0)
-
-        file = open(filename, "r")
-        actual = file.read()
-        file.close()
-
-        expected = "telegraf: BOTH\n"
-        self.assertEqual(actual, expected)
-
     def test_replace_missing_arg(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -390,21 +346,6 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep1: 46\nkey2: false\nkey3:\n- e\n- f\n- g\n"
         self.assertEqual(actual, expected)
 
-    def test_replace_empty_file(self):
-        filename = "/tmp/so-yaml_test-replace-empty.yaml"
-        file = open(filename, "w")
-        file.close()
-
-        code = soyaml.replace([filename, "telegraf.output", "BOTH"])
-        self.assertEqual(code, 0)
-
-        file = open(filename, "r")
-        actual = file.read()
-        file.close()
-
-        expected = "telegraf:\n  output: BOTH\n"
-        self.assertEqual(actual, expected)
-
     def test_convert(self):
         self.assertEqual(soyaml.convertType("foo"), "foo")
         self.assertEqual(soyaml.convertType("foo.bar"), "foo.bar")
@@ -565,18 +506,6 @@ class TestRemove(unittest.TestCase):
             self.assertEqual(result, 2)
             self.assertEqual("", mock_stdout.getvalue())
 
-    def test_get_empty_file(self):
-        with patch('sys.stdout', new=StringIO()) as mock_stdout:
-            with patch('sys.stderr', new=StringIO()) as mock_stderr:
-                filename = "/tmp/so-yaml_test-get-empty.yaml"
-                file = open(filename, "w")
-                file.close()
-
-                result = soyaml.get([filename, "telegraf.output"])
-                self.assertEqual(result, 2)
-                self.assertEqual("", mock_stdout.getvalue())
-                self.assertIn("Key 'telegraf.output' not found by so-yaml.py", mock_stderr.getvalue())
-
     def test_get_usage(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -1062,29 +991,3 @@ class TestLoadYaml(unittest.TestCase):
                     soyaml.loadYaml("/tmp/so-yaml_test-unreadable.yaml")
                     sysmock.assert_called_with(1)
                     self.assertIn("Error reading file", mock_stderr.getvalue())
-
-    def test_load_yaml_empty_file(self):
-        filename = "/tmp/so-yaml_test-load-empty.yaml"
-        file = open(filename, "w")
-        file.close()
-
-        result = soyaml.loadYaml(filename)
-        self.assertEqual(result, {})
-
-    def test_load_yaml_whitespace_only(self):
-        filename = "/tmp/so-yaml_test-load-whitespace.yaml"
-        file = open(filename, "w")
-        file.write("   \n\n  \n")
-        file.close()
-
-        result = soyaml.loadYaml(filename)
-        self.assertEqual(result, {})
-
-    def test_load_yaml_comments_only(self):
-        filename = "/tmp/so-yaml_test-load-comments.yaml"
-        file = open(filename, "w")
-        file.write("# Just a comment\n# Another comment\n")
-        file.close()
-
-        result = soyaml.loadYaml(filename)
-        self.assertEqual(result, {})

salt/manager/tools/sbin/soup

@@ -28,7 +28,6 @@ INSTALLEDSALTVERSION=$(salt --versions-report | grep Salt: | awk '{print $2}')
 # percentage like "25%"). Empty means so-soup-grid-highstate uses the salt:auto_apply:batch
 # pillar default.
 BATCHSIZE=
-DEFAULT_DOCKER_RANGE='172.17.1.0/24'
 SOUP_LOG=/root/soup.log
 SOUP_DEBUG_LOG=/root/soup-debug.log
 WHATWOULDYOUSAYYAHDOHERE=soup
@@ -121,6 +120,9 @@ check_err() {
       161)
         echo 'Required intermediate Elasticsearch upgrade not complete'
       ;;
+      162)
+        echo 'One or more Elastic Agent nodes do not support the x86-64-v3 CPU instruction set'
+      ;;
       170)
         echo "Intermediate upgrade completed successfully to $next_step_so_version, but next soup to Security Onion $originally_requested_so_version could not be started automatically."
         echo "Start soup again manually to continue the upgrade to Security Onion $originally_requested_so_version."
@@ -348,6 +350,83 @@ check_cluster_health() {
   exit 0
 }
 
+no_soup_for_you() {
+  echo ""
+  echo "No soup for you!"
+  exit 162
+}
+
+check_cpu_compatibility() {
+  # Roles running a container built from the so-elastic-agent image; mirrors the
+  # elasticagent and elasticfleet entries in salt/reactor/pillar_push_map.yaml.
+  local cpu_target='G@role:so-heavynode or G@role:so-eval or G@role:so-fleet or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
+  local expected_nodes cpu_results node result confirm
+  local -a unsupported=() offline=()
+
+  echo "Checking that Elastic Agent nodes support the x86-64-v3 CPU instruction set now required by Elastic."
+
+  if [[ "$SKIP_CPU_CHECK" == "true" ]]; then
+    printf "\nSkipping the x86-64-v3 CPU check because --skip-cpu-check was specified.\n\n"
+    return
+  fi
+
+  # Nodes that never answer are absent from the results, so diff against who should have.
+  expected_nodes=$(salt -C "$cpu_target" --preview-target --out=json 2>/dev/null | jq -r '.[]?') || true
+  if [[ -z "$expected_nodes" ]]; then
+    printf "\nCould not determine which nodes run the Elastic Agent, so the x86-64-v3 CPU check cannot run.\n"
+    no_soup_for_you
+  fi
+
+  cpu_results=$(salt -t 30 -C "$cpu_target" cmd.run "/lib64/ld-linux-x86-64.so.2 --help | grep x86-64-v3" --out=json 2>/dev/null) || true
+
+  while IFS= read -r node; do
+    [[ -z "$node" ]] && continue
+    result=$(jq -r --arg node "$node" '.[$node] // empty' <<< "$cpu_results" 2>/dev/null)
+    if [[ -z "$result" || "$result" == *"did not return"* ]]; then
+      offline+=("$node")
+    elif [[ "$result" != *"x86-64-v3 (supported"* ]]; then
+      # glibc appends "(supported, searched)" only when supported; the open paren keeps
+      # this from matching a future "(unsupported".
+      unsupported+=("$node")
+    fi
+  done <<< "$expected_nodes"
+
+  if [[ ${#unsupported[@]} -eq 0 && ${#offline[@]} -eq 0 ]]; then
+    printf "\nAll Elastic Agent nodes support x86-64-v3. We can proceed with SOUP.\n\n"
+    return
+  fi
+
+  echo ""
+  if [[ ${#unsupported[@]} -gt 0 ]]; then
+    echo "The following node(s) do NOT support the x86-64-v3 CPU instruction set:"
+    printf '  %s\n' "${unsupported[@]}"
+    echo ""
+    echo "Upstream Elastic now builds its binaries for x86-64-v3, so these nodes can no"
+    echo "longer run Elastic. Upgrading them WILL BREAK them."
+    echo ""
+  fi
+  if [[ ${#offline[@]} -gt 0 ]]; then
+    echo "The following node(s) did not respond and could not be checked:"
+    printf '  %s\n' "${offline[@]}"
+    echo ""
+    echo "These nodes are offline, so we cannot confirm they support x86-64-v3, which"
+    echo "upstream Elastic now requires."
+    echo ""
+  fi
+
+  if [[ -n $UNATTENDED ]]; then
+    echo "Unattended mode cannot prompt for an override. Re-run soup interactively, or pass --skip-cpu-check to bypass this check."
+    no_soup_for_you
+  fi
+
+  read -rp "Type 'override' to continue anyway, or press Enter to exit: " confirm
+  if [[ "${confirm,,}" == "override" ]]; then
+    printf "\nOverride accepted. Continuing at your own risk.\n\n"
+  else
+    no_soup_for_you
+  fi
+}
+
 check_fleet_server() {
   echo "Checking that Elastic Fleet Server is responding."
   # Modeled on the wait_for_so-elastic-fleet state check in elasticfleet/enabled.sls,
@@ -526,7 +605,6 @@ preupgrade_changes() {
     [[ "$INSTALLEDVERSION" == "3.0.0" ]] && up_to_3.1.0
     [[ "$INSTALLEDVERSION" == "3.1.0" ]] && up_to_3.2.0
     [[ "$INSTALLEDVERSION" == "3.2.0" ]] && up_to_3.3.0
-    [[ "$INSTALLEDVERSION" == "3.3.0" ]] && up_to_3.4.0
     true
 }
 
@@ -545,8 +623,6 @@ postupgrade_changes() {
     [[ "$POSTVERSION" == "3.0.0" ]] && post_to_3.1.0
     [[ "$POSTVERSION" == "3.1.0" ]] && post_to_3.2.0
     [[ "$POSTVERSION" == "3.2.0" ]] && post_to_3.3.0
-    [[ "$POSTVERSION" == "3.3.0" ]] && post_to_3.4.0
-    [[ "$POSTVERSION" == "3.4.0" ]] && post_to_3.5.0
     # All applicable post-upgrade steps completed; clear the resume marker.
     rm -f "$POSTVERSION_FILE"
     true
@@ -1052,6 +1128,9 @@ post_to_3.2.0() {
 
 ### 3.3.0 Scripts ###
 up_to_3.3.0() {
+  # download 9.4.5 elastic agent packages
+  determine_elastic_agent_upgrade
+  
   # remove existing (patched) elasticsearch index template to match integration naming change
   if ! remove_elasticsearch_index_template "so-logs-sentinel_one_cloud_funnel.login" "sentinel_one_cloud_funnel.login changed to sentinel_one_cloud_funnel.logins"; then
     FINAL_MESSAGE_QUEUE+=("WARNING: Unable to automatically remove the so-logs-sentinel_one_cloud_funnel.login index template. This step can be performed manually using the following command:")
@@ -1066,166 +1145,34 @@ telegraf_repair() {
   # when there is something to repair, so everyone else is left alone.
   local repair=/usr/sbin/so-telegraf-repair
   [[ -x "$repair" ]] || return 0
-  local state
-  state=$(docker inspect -f '{{.State.Running}} {{.State.Restarting}}' so-postgres 2>/dev/null) || return 0
-  if [[ "$state" != "true false" ]]; then
-    echo "  so-postgres is not running; skipping the Telegraf partition check."
-    FINAL_MESSAGE_QUEUE+=("WARNING: so-postgres is not running, so Telegraf partitions were not checked. If /nsm is full, follow \"Telegraf Partition Repair\" at:")
-    FINAL_MESSAGE_QUEUE+=("    - https://securityonion.net/docs/postgresql")
-    return 0
-  fi
+  docker ps --format '{{.Names}}' | grep -qx so-postgres || return 0
 
   echo "Checking Telegraf metric partitions."
-  local out status=0
-  out=$("$repair" --check 2>&1) || status=$?
-  echo "$out" >> "$SOUP_LOG"
+  local status=0
+  "$repair" --check >> "$SOUP_LOG" 2>&1 || status=$?
   case "$status" in
     0) echo "  Telegraf partitions are healthy; nothing to repair." ;;
     1) echo "  Repairing stalled Telegraf partitions."
-       if ! "$repair" --yes; then
-         echo "  warning: so-telegraf-repair failed; run it manually" >&2
-         FINAL_MESSAGE_QUEUE+=("WARNING: Telegraf partition repair failed; Postgres metrics will keep filling /nsm until it is repaired:")
-         FINAL_MESSAGE_QUEUE+=("    - sudo so-telegraf-repair")
-       fi ;;
-    2) echo "  Skipping: $(tail -n 1 <<<"$out")" ;;
-    *) echo "  warning: could not check Telegraf partitions" >&2
-       FINAL_MESSAGE_QUEUE+=("WARNING: Telegraf partitions could not be checked during the upgrade; run:")
-       FINAL_MESSAGE_QUEUE+=("    - sudo so-telegraf-repair --check") ;;
+       "$repair" --yes \
+         || echo "  warning: so-telegraf-repair failed; run it manually" >&2 ;;
+    *) echo "  Skipping; Telegraf is not storing metrics in Postgres on this host." ;;
   esac
 }
 
 post_to_3.3.0() {
   # Recollate again since some internal DBs were excluded during 3.2.0 soup
   recollate_postgres
-  
+
+  # Generate 9.4.5 elastic agent installers
+  echo "Regenerating Elastic Agent Installers"
+  /sbin/so-elastic-agent-gen-installers
+
   telegraf_repair
 
   set_postversion 3.3.0
 }
 ### 3.3.0 End ###
 
-### 3.4.0 Scripts ###
-up_to_3.4.0() {
-  # download 9.4.8 elastic agent packages
-  determine_elastic_agent_upgrade
-  
-  set_soauth_range
-
-  echo "Removing so-kratos, so-hydra and so-soc so they are recreated on the soauth network."
-  docker rm -f so-kratos so-hydra so-soc >> $SOUP_LOG 2>&1
-
-  for template in so-metrics-logstash.node so-metrics-logstash.stack_monitoring.node; do
-    if ! remove_elasticsearch_index_template "$template" "logstash node and node_cel index patterns reversed"; then
-      FINAL_MESSAGE_QUEUE+=("WARNING: Unable to automatically remove the $template index template. Addon integration templates may fail to load until it is removed:")
-      FINAL_MESSAGE_QUEUE+=("    - sudo so-elasticsearch-query _index_template/$template -XDELETE && so-checkin")
-    fi
-  done
-
-  INSTALLEDVERSION=3.4.0
-}
-
-set_soauth_range() {
-  local pillar_file=/opt/so/saltstack/local/pillar/docker/soc_docker.sls
-  local current_range suggested authnet authgw input
-
-  [[ -f "$pillar_file" ]] || return 0
-
-  current_range=$(so-yaml.py get -r "$pillar_file" docker.range 2>/dev/null) || return 0
-
-  # A default range gets the 172.17.2.0/24 from docker/defaults.yaml, same as a fresh
-  # install, so there is nothing to ask about.
-  [[ -n "$current_range" && "$current_range" != "$DEFAULT_DOCKER_RANGE" ]] || return 0
-
-  if so-yaml.py get -r "$pillar_file" docker.networks.soauth.range >/dev/null 2>&1; then
-    return 0
-  fi
-
-  suggested=$(echo "${current_range%%/*}" | awk -F'.' '{ printf "%s.%s.%s.%s", $1, $2, ($3 + 1) % 256, $4 }')
-
-  if [[ -z $UNATTENDED ]]; then
-    echo ""
-    echo "This grid uses a custom Docker range ($current_range). The authentication"
-    echo "services are moving to their own isolated network, which needs a second /24"
-    echo "that does not overlap it."
-    echo ""
-    while :; do
-      read -rp "Enter the network without the /24 suffix, or press Enter for ${suggested}: " input
-      [[ -z "$input" ]] && input="$suggested"
-      if valid_soauth_range "$input" "$current_range"; then
-        authnet="$input"
-        break
-      fi
-      echo "That range must be a valid IPv4 network, must not be within 172.17.0.0/24, and must not overlap ${current_range}."
-    done
-  else
-    if ! valid_soauth_range "$suggested" "$current_range"; then
-      FINAL_MESSAGE_QUEUE+=("WARNING: Unable to pick a range for the authentication network alongside $current_range. Set it manually before the next highstate:")
-      FINAL_MESSAGE_QUEUE+=("    - so-yaml.py add $pillar_file docker.networks.soauth.range <network>/24")
-      FINAL_MESSAGE_QUEUE+=("    - so-yaml.py add $pillar_file docker.networks.soauth.gateway <gateway>")
-      return 0
-    fi
-    authnet="$suggested"
-    FINAL_MESSAGE_QUEUE+=("NOTE: The authentication services moved to an isolated Docker network and were assigned ${authnet}/24.")
-    FINAL_MESSAGE_QUEUE+=("    - If that conflicts with your environment, update docker.networks.soauth in $pillar_file and run so-checkin.")
-  fi
-
-  authgw=$(echo "$authnet" | awk -F'.' '{print $1,$2,$3,1}' OFS='.')
-
-  echo "Assigning the authentication network the range ${authnet}/24."
-  so-yaml.py add "$pillar_file" docker.networks.soauth.range "${authnet}/24" >> $SOUP_LOG 2>&1
-  so-yaml.py add "$pillar_file" docker.networks.soauth.gateway "$authgw" >> $SOUP_LOG 2>&1
-}
-
-valid_soauth_range() {
-  local candidate=$1 docker_range=$2
-
-  valid_ip4 "$candidate" || return 1
-  [[ $candidate =~ ^172\.17\.0\. ]] && return 1
-  [[ "${candidate}/24" == "$docker_range" ]] && return 1
-  return 0
-}
-
-post_to_3.4.0() {
-  # Generate 9.4.8 elastic agent installers
-  echo "Regenerating Elastic Agent Installers"
-  /sbin/so-elastic-agent-gen-installers
-  
-  for idx in "metrics-logstash.node-default" "metrics-logstash.stack_monitoring.node-default"; do
-    rollover_index "$idx"
-  done
-
-  add_detection_runtime_fields
-
-  remove_frozen_ca_bundles
-
-  set_postversion 3.4.0
-}
-
-remove_frozen_ca_bundles() {
-  rm -f /opt/so/saltstack/local/salt/elasticsearch/cacerts /opt/so/saltstack/local/salt/elasticsearch/tls-ca-bundle.pem >> $SOUP_LOG 2>&1
-}
-
-add_detection_runtime_fields() {
-  local template=$DEFAULT_SALT_DIR/salt/elasticsearch/templates/component/so/detection-mappings.json
-  local runtime
-
-  runtime=$(jq -c '{runtime: .template.mappings.runtime}' "$template")
-  if ! so-elasticsearch-query so-detection/_mapping -XPUT -d "$runtime" --retry 3 --retry-delay 5 --fail >> $SOUP_LOG 2>&1; then
-    FINAL_MESSAGE_QUEUE+=("WARNING: Unable to add the Sigma search fields to the so-detection index. Searches on so_detection.sigmaKind will match nothing until they are added:")
-    FINAL_MESSAGE_QUEUE+=("    - sudo so-elasticsearch-query so-detection/_mapping -XPUT -d \"\$(jq -c '{runtime: .template.mappings.runtime}' $template)\"")
-  fi
-}
-### 3.4.0 End ###
-
-### 3.5.0 Scripts ###
-
-post_to_3.5.0() {
-  telegraf_repair
-
-  set_postversion 3.5.0
-}
-### 3.5.0 End ###
-
 
 repo_sync() {
   echo "Sync the local repo."
@@ -1498,10 +1445,9 @@ verify_es_version_compatibility() {
       ["8.18.4"]="8.18.6 8.18.8 9.0.8"
 	    ["8.18.6"]="8.18.8 9.0.8"
 	    ["8.18.8"]="9.0.8"
-      ["9.0.8"]="9.3.3 9.3.7 9.4.5 9.4.8"
-      ["9.3.3"]="9.3.7 9.4.5 9.4.8"
-      ["9.3.7"]="9.4.5 9.4.8"
-      ["9.4.5"]="9.4.8"
+      ["9.0.8"]="9.3.3 9.3.7 9.4.5"
+      ["9.3.3"]="9.3.7 9.4.5"
+      ["9.3.7"]="9.4.5"
     )
 
     # Elasticsearch MUST upgrade through these versions
@@ -2112,6 +2058,8 @@ main() {
   echo "Let's see if we need to update Security Onion."
   upgrade_check
 
+  check_cpu_compatibility
+
   upgrade_space
 
   echo "Verifying Elasticsearch version compatibility across the grid before upgrading."
@@ -2390,6 +2338,17 @@ fi
   echo "### soup has been served at $(date) ###"
 }
 
+SKIP_CPU_CHECK=false
+declare -a SOUP_ARGS=()
+for arg in "$@"; do
+  if [[ "$arg" == "--skip-cpu-check" ]]; then
+    SKIP_CPU_CHECK=true
+  else
+    SOUP_ARGS+=("$arg")
+  fi
+done
+set -- "${SOUP_ARGS[@]}"
+
 while getopts ":b:f:y" opt; do
   case ${opt} in
     b )
@@ -2413,7 +2372,7 @@ while getopts ":b:f:y" opt; do
       ISOLOC="$OPTARG"
     ;;
     \? )
-      echo "Usage: soup [-b] [-y] [-f <iso location>]"
+      echo "Usage: soup [-b] [-y] [-f <iso location>] [--skip-cpu-check]"
       exit 1
     ;;
     : )

salt/nginx/config.sls

@@ -57,8 +57,8 @@ nginx_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://nginx/tools/sbin
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939
     - file_mode: 755
 
 #nginx_sbin_jinja:

salt/nginx/enabled.sls

@@ -6,12 +6,10 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   from 'nginx/map.jinja' import NGINXMERGED %}
 
 include:
-  - ca.trust
   - nginx.ssl
   - nginx.config
   - nginx.sostatus
@@ -49,14 +47,13 @@ so-nginx:
       {% endfor %}
     {% endif %}
     - binds:
-      - {{ CATRUST.pem }}:/etc/ssl/certs/ca-certificates.crt:ro
       - /opt/so/conf/nginx/nginx.conf:/etc/nginx/nginx.conf:ro
       - /opt/so/log/nginx/:/var/log/nginx:rw
       - /opt/so/tmp/nginx/:/var/lib/nginx:rw
       - /opt/so/tmp/nginx/:/run:rw
-      - /nsm/elastic-fleet/artifacts/:/opt/socore/elastic-artifacts/artifacts:ro
-      {% if GLOBALS.is_manager %}
       - /nsm/elastic-fleet/so_agent-installers/:/opt/socore/html/packages
+      - /nsm/elastic-fleet/artifacts/:/opt/socore/html/artifacts 
+      {% if GLOBALS.is_manager %}
       - /etc/pki/managerssl.crt:/etc/pki/nginx/server.crt:ro
       - /etc/pki/managerssl.key:/etc/pki/nginx/server.key:ro
       # ATT&CK Navigator binds
@@ -92,7 +89,6 @@ so-nginx:
       - {{ BINDING }}
       {% endfor %}
     - watch:
-      - cmd: ca_trust_extract
       - file: nginxconf
       - file: nginxconfdir
       {% if GLOBALS.is_manager %}

salt/nginx/etc/nginx.conf

@@ -4,8 +4,6 @@
 {%- set role = grains.id.split('_') | last %}
 {%- set influxpass = salt['pillar.get']('secrets:influx_pass') %}
 {%- set influxauth = ('so:' + influxpass) | base64_encode %}
-{%- set all_names = [GLOBALS.hostname, GLOBALS.url_base] + NGINXMERGED.ssl.alt_names %}
-{%- set full_server_name = all_names | unique | join(' ') %}
 
 worker_processes auto;
 error_log /var/log/nginx/error.log;
@@ -41,31 +39,52 @@ http {
 
 	include /etc/nginx/conf.d/*.conf;
 
+	{%- if role in ['fleet'] %}
+
+	server {
+		listen 8443;
+		server_name {{ GLOBALS.hostname }};
+		root /opt/socore/html;
+		location /artifacts/ {
+			try_files $uri =206;
+			proxy_read_timeout    90;
+			proxy_connect_timeout 90;
+			proxy_set_header      Host $host;
+			proxy_set_header      X-Real-IP $remote_addr;
+			proxy_set_header      X-Forwarded-For $proxy_add_x_forwarded_for;
+			proxy_set_header      Proxy "";
+			proxy_set_header      X-Forwarded-Proto $scheme;
+		}
+	}
+
+    {%- endif %}
+
 	{%- if GLOBALS.is_manager %}
+	{%- set all_names = [GLOBALS.hostname, GLOBALS.url_base] + NGINXMERGED.ssl.alt_names %}
+	{%- set full_server_name = all_names | unique | join(' ') %}
+
 	server {
 		listen 80 default_server;
 		server_name _;
 		return 307 https://{{ GLOBALS.url_base }}$request_uri;
 	}
-  {%- endif %}
-  {%- if GLOBALS.is_manager or role == 'fleet' %}
+
 	server {
 		listen 8443;
-    {%- if GLOBALS.is_manager %}
 		server_name {{ full_server_name }};
-    {%- else %}
-    server_name {{ GLOBALS.hostname }};
-    {%- endif %}
-		root /opt/socore/elastic-artifacts;
+		root /opt/socore/html;
 		location /artifacts/ {
-			try_files $uri =404;
-		}
-		location / {
-			return 404;
+			try_files $uri =206;
+			proxy_read_timeout    90;
+			proxy_connect_timeout 90;
+			proxy_set_header      Host $host;
+			proxy_set_header      X-Real-IP $remote_addr;
+			proxy_set_header      X-Forwarded-For $proxy_add_x_forwarded_for;
+			proxy_set_header      Proxy "";
+			proxy_set_header      X-Forwarded-Proto $scheme;
 		}
 	}
-  {%- endif %}
-  {%- if GLOBALS.is_manager %}
+
 	server {
 		listen 443 ssl default_server;
 		http2 on;
@@ -164,7 +183,7 @@ http {
 		ssl_prefer_server_ciphers on;
 		ssl_protocols TLSv1.2 TLSv1.3;
 
-		location ~* (^/login|^/login/.*|^/js/.*|^/css/.*|^/images/.*|^/pages/.*|^/docs/.*) {
+		location ~* (^/login/.*|^/js/.*|^/css/.*|^/images/.*|^/pages/.*|^/docs/.*) {
 			proxy_pass            http://{{ GLOBALS.manager }}:9822;
 			proxy_read_timeout    90;
 			proxy_connect_timeout 90;

salt/postgres/defaults.yaml

@@ -17,4 +17,3 @@ postgres:
     log_min_messages: 'warning'
     shared_preload_libraries: pg_cron
     cron.database_name: postgres
-    cron.host: /run/postgresql

salt/postgres/enabled.sls

@@ -6,12 +6,10 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{%   from 'ca/trust.map.jinja' import CATRUST %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
 {%   set SO_POSTGRES_USER = salt['pillar.get']('postgres:auth:users:so_postgres_user:user', 'so_postgres') %}
 
 include:
-  - ca.trust
   - postgres.auth
   - postgres.ssl
   - postgres.config
@@ -44,7 +42,6 @@ so-postgres:
         {% endfor %}
       {% endif %}
     - binds:
-      - {{ CATRUST.dir }}
       - /opt/so/log/postgres/:/log:rw
       - /nsm/postgres:/var/lib/postgresql/data:rw
       - /opt/so/conf/postgres/postgresql.conf:/conf/postgresql.conf:ro
@@ -72,7 +69,6 @@ so-postgres:
     {%   endfor %}
     {% endif %}
     - watch:
-      - cmd: ca_trust_extract
       - file: postgresconf
       - file: postgreshba
       - file: postgresinitdb

salt/postgres/soc_postgres.yaml

@@ -87,9 +87,3 @@ postgres:
       global: True
       advanced: True
       helpLink: postgres
-    cron.host:
-      description: Where pg_cron connects to run scheduled jobs such as Telegraf partition maintenance. Must be the container's PostgreSQL socket directory, /run/postgresql, because pg_cron connects without a password and only local socket connections are trusted. Any other value makes every scheduled job fail. Changing it restarts PostgreSQL.
-      readonly: True
-      global: True
-      advanced: True
-      helpLink: postgres

salt/postgres/tools/sbin/so-stats-show

@@ -52,7 +52,7 @@ if [ -n "$FILTER_HOST" ] && ! [[ "$FILTER_HOST" =~ $HOST_RE ]]; then
 fi
 
 so_psql() {
-  docker exec -e PGOPTIONS='-c application_name=so-stats-show' so-postgres psql -U so_maint_telegraf -d so_telegraf -At -F $'\t' "$@"
+  docker exec so-postgres psql -U postgres -d so_telegraf -At -F $'\t' "$@"
 }
 
 if ! docker exec so-postgres psql -U postgres -lqt 2>/dev/null | cut -d\| -f1 | grep -qw so_telegraf; then
@@ -60,11 +60,6 @@ if ! docker exec so-postgres psql -U postgres -lqt 2>/dev/null | cut -d\| -f1 |
   exit 2
 fi
 
-if ! docker exec so-postgres psql -U postgres -tAc "SELECT 1 FROM pg_roles WHERE rolname = 'so_maint_telegraf'" 2>/dev/null | grep -q 1; then
-  echo "The so_maint_telegraf role is missing; run a highstate."
-  exit 1
-fi
-
 table_exists() {
   local table="$1"
   [ -n "$(so_psql -c "SELECT 1 FROM information_schema.tables WHERE table_schema='${SCHEMA}' AND table_name='${table}' LIMIT 1;")" ]

salt/postgres/tools/sbin/so-telegraf-postgres

@@ -4,18 +4,15 @@ set -e
 # Provision Telegraf state inside the so-postgres container.
 # Usage: so-telegraf-postgres <subcommand>
 #   create_db    Ensure the so_telegraf database exists.
-#   group_role   Provision the so_telegraf group role, the so_maint_telegraf
-#                maintenance login role, telegraf/partman schemas, pg_partman,
-#                the so_admin maintenance routines, and the hourly pg_cron
-#                maintenance job.
+#   group_role   Provision the so_telegraf group role, telegraf/partman schemas,
+#                pg_partman, the so_admin maintenance routines, and the hourly
+#                pg_cron maintenance job.
 #   user         Create or update a per-minion login role granted to so_telegraf.
 #                Env: ROLE_USER, ROLE_PASS.
 #   retention    Reconcile partman retention and premake on telegraf parents.
 #                Env: RETENTION_DAYS.
-#   maintenance  Drain default partitions and run partman maintenance, as
-#                so_maint_telegraf.
-#   check        Report partition health, as so_maint_telegraf. Non-zero if any
-#                parent is unhealthy.
+#   maintenance  Drain default partitions and run partman maintenance.
+#   check        Report partition health. Non-zero if any parent is unhealthy.
 #
 # A default partition holding rows for a day blocks creating that day's child,
 # so maintenance drains defaults before calling partman. Use so-telegraf-repair
@@ -23,10 +20,6 @@ set -e
 
 cmd="${1:?subcommand required}"
 
-# Long enough for an hourly maintenance run to release its locks, short enough
-# that soup and admins are not left hanging.
-LOCK_TIMEOUT=60s
-
 case "$cmd" in
   create_db)
     if ! docker exec so-postgres psql -U postgres -tAc \
@@ -37,9 +30,7 @@ case "$cmd" in
     ;;
 
   group_role)
-    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -v lock_timeout="$LOCK_TIMEOUT" \
-      -U postgres -d so_telegraf <<'EOSQL'
-SET lock_timeout = :'lock_timeout';
+    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
 DO $$
 BEGIN
     IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = 'so_telegraf') THEN
@@ -47,17 +38,6 @@ BEGIN
     END IF;
 END
 $$;
-DO $$
-BEGIN
-    IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = 'so_maint_telegraf') THEN
-        CREATE ROLE so_maint_telegraf;
-    END IF;
-END
-$$;
-ALTER ROLE so_maint_telegraf LOGIN NOSUPERUSER NOCREATEDB NOCREATEROLE NOREPLICATION NOBYPASSRLS PASSWORD NULL;
-GRANT so_telegraf TO so_maint_telegraf;
-ALTER ROLE so_maint_telegraf SET role = so_telegraf;
-ALTER ROLE so_maint_telegraf SET search_path = pg_catalog;
 GRANT CONNECT ON DATABASE so_telegraf TO so_telegraf;
 CREATE SCHEMA IF NOT EXISTS telegraf AUTHORIZATION so_telegraf;
 GRANT USAGE, CREATE ON SCHEMA telegraf TO so_telegraf;
@@ -78,82 +58,44 @@ ALTER DEFAULT PRIVILEGES IN SCHEMA partman
 ALTER DEFAULT PRIVILEGES IN SCHEMA partman
     GRANT USAGE, SELECT, UPDATE ON SEQUENCES TO so_telegraf;
 
--- Owned by postgres so no Telegraf role can create objects here; the routines
--- run with the caller's privileges.
+-- pg_cron runs these as postgres, so they must not sit in a schema any
+-- Telegraf role can create objects in.
 CREATE SCHEMA IF NOT EXISTS so_admin AUTHORIZATION postgres;
 REVOKE ALL ON SCHEMA so_admin FROM PUBLIC;
 
--- Resolved through pg_inherits, never by name, so a view or a table that only
--- carries the _default name is never read or written.
-CREATE OR REPLACE FUNCTION so_admin.telegraf_defaults()
-RETURNS TABLE (
-    parent_table  regclass,
-    default_part  regclass,
-    has_rows      boolean,
-    default_size  bigint
-)
-LANGUAGE plpgsql
-STABLE
-SECURITY INVOKER
-AS $func$
-DECLARE
-    r  record;
-BEGIN
-    FOR r IN
-        SELECT to_regclass(pc.parent_table) AS pt
-        FROM partman.part_config pc
-        WHERE pc.parent_table LIKE 'telegraf.%'
-        ORDER BY pc.parent_table
-    LOOP
-        CONTINUE WHEN r.pt IS NULL;
-        parent_table := r.pt;
-
-        SELECT c.oid::regclass INTO default_part
-        FROM pg_catalog.pg_inherits i
-        JOIN pg_catalog.pg_class c ON c.oid = i.inhrelid
-        WHERE i.inhparent = r.pt
-          AND c.relkind = 'r' AND c.relispartition
-          AND pg_catalog.pg_get_expr(c.relpartbound, c.oid) = 'DEFAULT';
-
-        IF default_part IS NULL THEN
-            has_rows     := false;
-            default_size := NULL;
-        ELSE
-            EXECUTE format('SELECT EXISTS (SELECT 1 FROM %s LIMIT 1)', default_part)
-                INTO has_rows;
-            default_size := pg_catalog.pg_total_relation_size(default_part);
-        END IF;
-
-        RETURN NEXT;
-    END LOOP;
-END;
-$func$;
-
 CREATE OR REPLACE PROCEDURE so_admin.telegraf_maintenance()
 LANGUAGE plpgsql
-SECURITY INVOKER
--- No SET clause: it would forbid the COMMITs below, so so_maint_telegraf pins search_path instead.
 AS $proc$
 DECLARE
-    r  record;
+    r          record;
+    v_default  text;
+    v_rows     bigint;
 BEGIN
     -- No per-parent EXCEPTION handler: partition_data_proc commits internally,
     -- and COMMIT is illegal while a subtransaction is active. A failing parent
     -- aborts the run and the next pass retries.
     FOR r IN
-        SELECT pc.parent_table, pc.retention, d.default_part, d.default_size
-        FROM so_admin.telegraf_defaults() d
-        JOIN partman.part_config pc ON to_regclass(pc.parent_table) = d.parent_table
-        WHERE d.default_part IS NOT NULL AND d.has_rows
-        ORDER BY pc.parent_table
+        SELECT parent_table, retention
+        FROM partman.part_config
+        WHERE parent_table LIKE 'telegraf.%'
+        ORDER BY parent_table
     LOOP
-        RAISE WARNING 'so_admin.telegraf_maintenance: % holds rows (%), draining',
-                      r.default_part, pg_size_pretty(r.default_size);
+        v_default := format('%I.%I',
+                            split_part(r.parent_table, '.', 1),
+                            split_part(r.parent_table, '.', 2) || '_default');
+
+        CONTINUE WHEN to_regclass(v_default) IS NULL;
+
+        EXECUTE format('SELECT count(*) FROM %s', v_default) INTO v_rows;
+        CONTINUE WHEN v_rows = 0;
+
+        RAISE WARNING 'so_admin.telegraf_maintenance: % rows stranded in %, draining',
+                      v_rows, v_default;
 
         -- Cheaper to delete expired rows than to repartition and then drop them.
         IF r.retention IS NOT NULL THEN
             EXECUTE format('DELETE FROM %s WHERE "time" < now() - %L::interval',
-                           r.default_part, r.retention);
+                           v_default, r.retention);
             COMMIT;
         END IF;
 
@@ -161,7 +103,7 @@ BEGIN
         CALL partman.partition_data_proc(
             p_parent_table := r.parent_table,
             p_loop_count   := 200,
-            p_source_table := r.default_part::text
+            p_source_table := v_default
         );
         COMMIT;
     END LOOP;
@@ -170,75 +112,58 @@ BEGIN
 END;
 $proc$;
 
-DROP FUNCTION IF EXISTS so_admin.telegraf_partition_status();
-CREATE FUNCTION so_admin.telegraf_partition_status()
+CREATE OR REPLACE FUNCTION so_admin.telegraf_partition_status()
 RETURNS TABLE (
-    parent_table      text,
-    oldest_child      date,
-    newest_child      date,
-    days_ahead        int,
-    retention         text,
-    default_has_rows  boolean,
-    default_size      text
+    parent_table  text,
+    oldest_child  date,
+    newest_child  date,
+    days_ahead    int,
+    retention     text,
+    default_rows  bigint,
+    default_size  text
 )
 LANGUAGE plpgsql
-STABLE
 AS $func$
 DECLARE
-    r  record;
+    r          record;
+    v_default  regclass;
 BEGIN
     FOR r IN
-        SELECT d.parent_table AS pt, d.has_rows, d.default_size AS size, pc.retention AS ret
-        FROM so_admin.telegraf_defaults() d
-        JOIN partman.part_config pc ON to_regclass(pc.parent_table) = d.parent_table
-        ORDER BY d.parent_table::text
+        SELECT pc.parent_table AS pt, pc.retention AS ret
+        FROM partman.part_config pc
+        WHERE pc.parent_table LIKE 'telegraf.%'
+        ORDER BY pc.parent_table
     LOOP
-        parent_table := r.pt::text;
+        parent_table := r.pt;
         retention    := r.ret;
 
-        SELECT min(x), max(x) INTO oldest_child, newest_child
+        SELECT min(d), max(d) INTO oldest_child, newest_child
         FROM (
-            SELECT to_date(substring(c.relname FROM '_p(\d{8})$'), 'YYYYMMDD') AS x
-            FROM pg_catalog.pg_inherits i
-            JOIN pg_catalog.pg_class c ON c.oid = i.inhrelid
-            WHERE i.inhparent = r.pt
-              AND pg_catalog.pg_get_expr(c.relpartbound, c.oid) <> 'DEFAULT'
+            SELECT to_date(substring(c.relname FROM '_p(\d{8})$'), 'YYYYMMDD') AS d
+            FROM pg_inherits i
+            JOIN pg_class c ON c.oid = i.inhrelid
+            WHERE i.inhparent = r.pt::regclass
+              AND pg_get_expr(c.relpartbound, c.oid) <> 'DEFAULT'
         ) s;
 
-        days_ahead       := newest_child - current_date;
-        default_has_rows := r.has_rows;
-        default_size     := pg_size_pretty(r.size);
+        days_ahead := newest_child - current_date;
+
+        v_default := to_regclass(format('%I.%I',
+                                        split_part(r.pt, '.', 1),
+                                        split_part(r.pt, '.', 2) || '_default'));
+        IF v_default IS NULL THEN
+            default_rows := NULL;
+            default_size := NULL;
+        ELSE
+            EXECUTE format('SELECT count(*) FROM %s', v_default::text) INTO default_rows;
+            default_size := pg_size_pretty(pg_total_relation_size(v_default));
+        END IF;
 
         RETURN NEXT;
     END LOOP;
 END;
 $func$;
 
-GRANT USAGE ON SCHEMA so_admin TO so_telegraf;
-GRANT EXECUTE ON FUNCTION so_admin.telegraf_defaults() TO so_telegraf;
-GRANT EXECUTE ON PROCEDURE so_admin.telegraf_maintenance() TO so_telegraf;
-GRANT EXECUTE ON FUNCTION so_admin.telegraf_partition_status() TO so_telegraf;
-
--- Partitions created by a superuser session (an older repair) belong to
--- postgres; partman acting as so_telegraf could not drop them.
-DO $$
-DECLARE
-    r  record;
-BEGIN
-    FOR r IN
-        SELECT n.nspname, c.relname
-        FROM pg_catalog.pg_class c
-        JOIN pg_catalog.pg_namespace n ON n.oid = c.relnamespace
-        WHERE c.relkind IN ('r', 'p')
-          AND (n.nspname = 'telegraf'
-               OR (n.nspname = 'partman' AND c.relname LIKE 'template\_telegraf\_%'))
-          AND c.relowner <> 'so_telegraf'::regrole
-    LOOP
-        EXECUTE format('ALTER TABLE %I.%I OWNER TO so_telegraf', r.nspname, r.relname);
-    END LOOP;
-END
-$$;
-
 -- Drop the registration older releases left in so_telegraf.
 SELECT CASE
          WHEN current_setting('cron.database_name', true) IS DISTINCT FROM current_database()
@@ -250,69 +175,20 @@ DROP EXTENSION pg_cron CASCADE;
 \endif
 EOSQL
 
-    stalled=false
-    probe_failed=false
-    if out=$(docker exec -e PGOPTIONS="-c lock_timeout=$LOCK_TIMEOUT" so-postgres \
-        psql -U so_maint_telegraf -d so_telegraf -tAc \
-        "SELECT coalesce(bool_or(has_rows), false) FROM so_admin.telegraf_defaults()"); then
-      case "$out" in
-        t) stalled=true ;;
-        f) stalled=false ;;
-        *) probe_failed=true ;;
-      esac
-    else
-      probe_failed=true
-    fi
-    if $probe_failed; then
-      echo "ERROR: could not check Telegraf default partitions; the maintenance job was not changed." >&2
-      exit 1
-    fi
-
     # Guarded on the live GUC so applying this before the postgresql.conf change
     # has restarted the container skips rather than failing.
-    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -v stalled="$stalled" \
-      -U postgres -d postgres <<'EOSQL'
+    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d postgres <<'EOSQL'
 SELECT CASE WHEN current_setting('cron.database_name', true) = current_database()
             THEN 'true' ELSE 'false' END AS cron_here \gset
 \if :cron_here
 CREATE EXTENSION IF NOT EXISTS pg_cron;
--- A highstate reconciles the job's definition but never its active flag; only so-telegraf-repair turns it on.
-BEGIN;
-SELECT coalesce(max(jobid)::text, '') AS jobid,
-       count(*) > 0 AS job_exists,
-       coalesce(bool_and(active), true) AS job_active
-FROM cron.job
-WHERE jobname = 'telegraf-partman-maintenance' AND username = 'so_maint_telegraf' \gset
-SELECT cron.unschedule(jobid) FROM cron.job
-WHERE jobname = 'telegraf-partman-maintenance' AND username <> 'so_maint_telegraf';
-\if :job_exists
-SELECT cron.alter_job(:jobid,
-  schedule := '17 * * * *',
-  command  := 'CALL so_admin.telegraf_maintenance()',
-  database := 'so_telegraf');
-\else
--- Registered inactive on a stalled grid so nothing drains the default
--- partitions before so-telegraf-repair truncates them.
+-- cron.schedule_in_database is idempotent by jobname.
 SELECT cron.schedule_in_database(
   'telegraf-partman-maintenance',
   '17 * * * *',
   'CALL so_admin.telegraf_maintenance()',
-  'so_telegraf',
-  'so_maint_telegraf',
-  NOT :'stalled'::boolean
+  'so_telegraf'
 );
-\endif
-UPDATE cron.job SET nodename = current_setting('cron.host')
-WHERE jobname = 'telegraf-partman-maintenance'
-  AND nodename IS DISTINCT FROM current_setting('cron.host');
-COMMIT;
-SELECT coalesce(bool_and(active), true) AS job_active
-FROM cron.job
-WHERE jobname = 'telegraf-partman-maintenance' AND username = 'so_maint_telegraf' \gset
-\if :job_active
-\else
-\echo 'WARNING: the Telegraf maintenance job is inactive; run ''sudo so-telegraf-repair''.'
-\endif
 \else
 \echo 'pg_cron metadata database is not `postgres` yet; skipping job registration.'
 \endif
@@ -371,7 +247,7 @@ EOSQL
     ;;
 
   maintenance)
-    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U so_maint_telegraf -d so_telegraf <<'EOSQL'
+    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
 SELECT CASE WHEN to_regproc('so_admin.telegraf_maintenance') IS NOT NULL
             THEN 'true' ELSE 'false' END AS has_proc \gset
 \if :has_proc
@@ -383,7 +259,7 @@ EOSQL
     ;;
 
   check)
-    docker exec -i so-postgres psql -U so_maint_telegraf -d so_telegraf <<'EOSQL'
+    docker exec -i so-postgres psql -U postgres -d so_telegraf <<'EOSQL'
 \pset border 2
 SELECT * FROM so_admin.telegraf_partition_status();
 EOSQL
@@ -402,9 +278,9 @@ LIMIT 5;
 \echo 'pg_cron is not installed in this database.'
 \endif
 EOSQL
-    unhealthy=$(docker exec so-postgres psql -U so_maint_telegraf -d so_telegraf -tAc \
+    unhealthy=$(docker exec so-postgres psql -U postgres -d so_telegraf -tAc \
       "SELECT count(*) FROM so_admin.telegraf_partition_status()
-       WHERE default_has_rows OR coalesce(days_ahead, -1) < 1")
+       WHERE coalesce(default_rows, 0) > 0 OR coalesce(days_ahead, -1) < 1")
     if [ "${unhealthy:-1}" != "0" ]; then
       echo "so-telegraf-postgres check: $unhealthy telegraf parent(s) unhealthy" >&2
       exit 1

salt/postgres/tools/sbin/so-telegraf-repair

@@ -11,38 +11,26 @@
 # maintenance once. Healthy grids are reported and left alone.
 #
 # Usage: so-telegraf-repair [--check] [--yes] [--no-restart]
-#   --check       Report health and change nothing. Also reports a missing
-#                 so_maint_telegraf role and a maintenance job that is missing
-#                 or inactive.
+#   --check       Report health and change nothing.
 #   --yes         Skip the confirmation prompt (for soup and other automation).
 #   --no-restart  Never restart so-postgres, even if pg_cron's launcher is dead.
 #
-# Repair mode (without --check) registers the so_maint_telegraf role and the
-# maintenance job if they are missing, pauses the job while it repairs, and
-# always leaves it active afterwards. Data work runs as so_maint_telegraf.
-#
 # Exit status:
 #   0  healthy, or repair completed
-#   1  repair is needed (--check), or the repair failed after it started
-#   2  skipped: Telegraf output is not Postgres, or so-postgres, so_telegraf or pg_partman is missing
-#   3  could not check, for example a connection error
+#   1  repair is needed (--check only)
+#   2  cannot run here: so-postgres, so_telegraf or pg_partman is missing
 
-set -eE
+set -e
 
 # Matches p_premake in telegraf.conf's create_parent template.
 PREMAKE=7
 JOB_NAME=telegraf-partman-maintenance
-MAINT_ROLE=so_maint_telegraf
-# Long enough for an hourly maintenance run to release its locks, short enough
-# that soup and admins are not left hanging.
-LOCK_TIMEOUT=60s
-PG_OPTS="-c lock_timeout=$LOCK_TIMEOUT -c application_name=so-telegraf-repair"
 
 CHECK_ONLY=false
 ASSUME_YES=false
 NO_RESTART=false
 
-usage() { sed -n '/^# Usage:/,/^#   3 /p' "$0" | sed 's/^# \?//'; }
+usage() { sed -n '/^# Usage:/,/^#   2 /p' "$0" | sed 's/^# \?//'; }
 
 while [[ $# -gt 0 ]]; do
   case "$1" in
@@ -50,153 +38,70 @@ while [[ $# -gt 0 ]]; do
     --yes|-y)          ASSUME_YES=true ;;
     --no-restart)      NO_RESTART=true ;;
     -h|--help)         usage; exit 0 ;;
-    *) echo "Unknown option: $1" >&2; usage >&2; exit 3 ;;
+    *) echo "Unknown option: $1" >&2; usage >&2; exit 2 ;;
   esac
   shift
 done
 
-# Strips C0 (except tab and newline), DEL and C1 characters, so names and
-# messages written with Telegraf credentials can't drive the terminal.
-sanitise() { LC_ALL=C tr -d '\000-\010\013-\037\177' | LC_ALL=C sed 's/\xc2[\x80-\x9f]//g'; }
+skip() { echo "$*"; exit 2; }
 
-ERR_FILE=$(mktemp)
-ERR_STATUS=3
-ERR_PREFIX="Could not check Telegraf partitions"
-job_id=
-restore_active=
-
-on_err() {
-  # Command substitutions inherit this trap; only the top level reports.
-  [[ $BASH_SUBSHELL -eq 0 ]] || exit "$ERR_STATUS"
-  local line
-  line=$(tail -n 1 "$ERR_FILE" | sanitise)
-  echo "$ERR_PREFIX: ${line:-command failed}" >&2
-  exit "$ERR_STATUS"
-}
-
-on_exit() {
-  if [[ -n "$restore_active" ]]; then
-    psql_cron -tAc "SELECT cron.alter_job($job_id, active := $restore_active)" >/dev/null || true
-  fi
-  rm -f "$ERR_FILE"
-}
-
-trap on_err ERR
-trap on_exit EXIT
-
-finish() { trap - ERR; exit "$1"; }
-skip() { echo "$*"; finish 2; }
-
-# Keeps the last stderr line for on_err while still showing all of it.
-capture() {
-  local rc=0
-  : >"$ERR_FILE"
-  "$@" 2>"$ERR_FILE" || rc=$?
-  sanitise <"$ERR_FILE" >&2
-  return "$rc"
-}
-
-psql_tg() {
-  capture docker exec -i -e PGOPTIONS="$PG_OPTS" so-postgres psql -U "$MAINT_ROLE" -d so_telegraf "$@"
-}
-psql_pg() {
-  capture docker exec -i -e PGOPTIONS="$PG_OPTS" so-postgres psql -U postgres -d postgres "$@"
-}
-psql_cron() {
-  capture docker exec -i -e PGOPTIONS="$PG_OPTS" so-postgres psql -U postgres -d "$cron_db" "$@"
-}
+psql_tg() { docker exec -i so-postgres psql -U postgres -d so_telegraf "$@"; }
+psql_pg() { docker exec -i so-postgres psql -U postgres -d postgres "$@"; }
 
+# query_to_xml so the per-table row counts need no helper function installed.
 REPORT="
+WITH parents AS (
+    SELECT pc.parent_table,
+           pc.premake,
+           split_part(pc.parent_table, '.', 1) AS sch,
+           split_part(pc.parent_table, '.', 2) AS tbl
+    FROM partman.part_config pc
+    WHERE pc.parent_table LIKE 'telegraf.%'
+), children AS (
+    SELECT p.parent_table,
+           max(to_date(substring(c.relname FROM '_p(\d{8})\$'), 'YYYYMMDD')) AS newest_child
+    FROM parents p
+    JOIN pg_class pt ON pt.oid = p.parent_table::regclass
+    JOIN pg_inherits i ON i.inhparent = pt.oid
+    JOIN pg_class c ON c.oid = i.inhrelid
+    WHERE pg_get_expr(c.relpartbound, c.oid) <> 'DEFAULT'
+    GROUP BY p.parent_table
+), defaults AS (
+    SELECT p.parent_table,
+           p.premake,
+           format('%I.%I', p.sch, p.tbl || '_default') AS default_table,
+           to_regclass(format('%I.%I', p.sch, p.tbl || '_default')) AS default_oid
+    FROM parents p
+)
 SELECT d.parent_table,
        c.newest_child,
        (c.newest_child - current_date) AS days_ahead,
-       pc.premake,
-       d.has_rows AS default_has_rows,
-       pg_size_pretty(d.default_size) AS default_size
-FROM so_admin.telegraf_defaults() d
-JOIN partman.part_config pc ON to_regclass(pc.parent_table) = d.parent_table
-LEFT JOIN LATERAL (
-    SELECT max(to_date(substring(ch.relname FROM '_p(\d{8})\$'), 'YYYYMMDD')) AS newest_child
-    FROM pg_inherits i
-    JOIN pg_class ch ON ch.oid = i.inhrelid
-    WHERE i.inhparent = d.parent_table
-      AND pg_get_expr(ch.relpartbound, ch.oid) <> 'DEFAULT'
-) c ON true
-ORDER BY d.parent_table::text
+       d.premake,
+       CASE WHEN d.default_oid IS NULL THEN NULL ELSE
+            (xpath('/row/cnt/text()',
+                   query_to_xml(format('SELECT count(*) AS cnt FROM %s', d.default_table),
+                                false, true, '')))[1]::text::bigint
+       END AS default_rows,
+       CASE WHEN d.default_oid IS NULL THEN NULL
+            ELSE pg_size_pretty(pg_total_relation_size(d.default_oid)) END AS default_size
+FROM defaults d
+LEFT JOIN children c ON c.parent_table = d.parent_table
+ORDER BY 1
 "
 
-print_report() {
-  local report
-  report=$(psql_tg -c "$REPORT")
-  sanitise <<<"$report"
-}
-
-has_cron() {
-  [[ -n "$cron_db" ]] || return 0
-  psql_cron -tAc "SELECT 1 FROM pg_extension WHERE extname = 'pg_cron'"
-}
-
-lookup_job() {
-  local cron
-  cron=$(has_cron)
-  [[ -n "$cron" ]] || return 0
-  psql_cron -tA -F '|' -c \
-    "SELECT jobid, active FROM cron.job
-      WHERE jobname = '$JOB_NAME' AND username = '$MAINT_ROLE'
-      ORDER BY jobid LIMIT 1"
-}
-
-output=$(capture salt-call pillar.get telegraf:output --out=newline_values_only)
-output=$(tr -d '[:space:]' <<<"$output" | tr '[:lower:]' '[:upper:]')
-output=${output:-INFLUXDB}
-case "$output" in
-  POSTGRES|BOTH) ;;
-  *) skip "Telegraf output is $(sanitise <<<"$output"); not checking Postgres partitions." ;;
-esac
-
-containers=$(capture docker ps --format '{{.Names}}')
-grep -qx so-postgres <<<"$containers" \
+docker ps --format '{{.Names}}' | grep -qx so-postgres \
   || skip "so-postgres is not running; nothing to repair."
-has_db=$(psql_pg -tAc "SELECT 1 FROM pg_database WHERE datname = 'so_telegraf'")
-[[ -n "$has_db" ]] \
+docker exec so-postgres psql -U postgres -tAc \
+  "SELECT 1 FROM pg_database WHERE datname='so_telegraf'" | grep -q 1 \
   || skip "The so_telegraf database does not exist; Telegraf is not writing to Postgres."
-
-# so_telegraf before the postgres state lands, postgres after.
-cron_db=$(psql_pg -tAc "SELECT current_setting('cron.database_name', true)")
-cron_db=$(tr -d '[:space:]' <<<"$cron_db")
-
-has_role=$(psql_pg -tAc "SELECT 1 FROM pg_roles WHERE rolname = '$MAINT_ROLE'")
-job=
-[[ "$cron_db" == postgres ]] && job=$(lookup_job)
-
-if [[ -z "$has_role" ]] && $CHECK_ONLY; then
-  echo "Repair is needed:"
-  echo "  * maintenance role $MAINT_ROLE is missing"
-  echo
-  echo "Re-run without --check to repair."
-  finish 1
-fi
-
-if ! $CHECK_ONLY && [[ -z "$has_role" || ( "$cron_db" == postgres && -z "$job" ) ]]; then
-  echo "Registering the maintenance role and job."
-  if ! /usr/sbin/so-telegraf-postgres group_role; then
-    echo "Could not register the maintenance job; run a highstate and try again." >&2
-    finish 3
-  fi
-  [[ "$cron_db" == postgres ]] && job=$(lookup_job)
-fi
-
-has_partman=$(psql_tg -tAc "SELECT 1 FROM pg_extension WHERE extname = 'pg_partman'")
-[[ -n "$has_partman" ]] \
+psql_tg -tAc "SELECT 1 FROM pg_extension WHERE extname='pg_partman'" | grep -q 1 \
   || skip "pg_partman is not installed in so_telegraf; nothing to repair."
 
 parents=$(psql_tg -tAc \
   "SELECT count(*) FROM partman.part_config WHERE parent_table LIKE 'telegraf.%'")
-counts=$(psql_tg -tAc \
-  "SELECT count(*) FILTER (WHERE default_has_rows) || '|' ||
-          count(*) FILTER (WHERE coalesce(days_ahead, -1) < 1)
-     FROM ( $REPORT ) t")
-IFS='|' read -r stranded behind <<<"$counts"
+stranded=$(psql_tg -tAc "SELECT coalesce(sum(default_rows), 0) FROM ( $REPORT ) t")
+behind=$(psql_tg -tAc \
+  "SELECT count(*) FROM ( $REPORT ) t WHERE coalesce(days_ahead, -1) < 1")
 # premake < 7, or infinite_time_partitions off: without the latter partman
 # refuses to premake forward across the gap the stall left behind.
 misconfigured=$(psql_tg -tAc \
@@ -210,24 +115,16 @@ launcher=$(psql_pg -tAc \
   "SELECT count(*) FROM pg_stat_activity
     WHERE backend_type ILIKE '%pg_cron%' OR application_name ILIKE '%pg_cron%'")
 
+# so_telegraf before the postgres state lands, postgres after.
+cron_db=$(docker exec so-postgres psql -U postgres -tAc \
+  "SELECT current_setting('cron.database_name', true)" | tr -d '[:space:]')
 last_run=never
-cron_installed=$(has_cron)
-if [[ -n "$cron_installed" ]]; then
-  run=$(psql_cron -tAc \
-    "SELECT d.status || ' at ' || d.start_time
+if [[ -n "$cron_db" ]]; then
+  last_run=$(docker exec so-postgres psql -U postgres -d "$cron_db" -tAc \
+    "SELECT coalesce(max(d.start_time)::text, 'never')
        FROM cron.job_run_details d JOIN cron.job j USING (jobid)
-      WHERE j.jobname = '$JOB_NAME'
-      ORDER BY d.start_time DESC LIMIT 1")
-  if [[ -n "$run" ]]; then
-    message=$(psql_cron -tAc \
-      "SELECT coalesce(d.return_message, '')
-         FROM cron.job_run_details d JOIN cron.job j USING (jobid)
-        WHERE j.jobname = '$JOB_NAME'
-        ORDER BY d.start_time DESC LIMIT 1")
-    message=$(sanitise <<<"$message")
-    message=${message//$'\n'/ }
-    last_run="$(sanitise <<<"$run"): ${message:0:200}"
-  fi
+      WHERE j.jobname = '$JOB_NAME'" 2>/dev/null | tr -d '[:space:]' || echo unknown)
+  [[ -n "$last_run" ]] || last_run=never
 fi
 
 # A grid that has never written a metric has nothing to recover, and an empty
@@ -235,67 +132,43 @@ fi
 restart_needed=false
 [[ "$launcher" -eq 0 && "$parents" -gt 0 && -n "$cron_db" ]] && restart_needed=true
 
-# group_role registers the job only in the postgres database.
-job_inactive=false
-if [[ "$cron_db" == postgres ]]; then
-  [[ -z "$job" || "${job##*|}" == f ]] && job_inactive=true
-fi
-
 repair_needed=false
 [[ "$stranded" -gt 0 ]] && repair_needed=true
 [[ "$behind" -gt 0 ]] && repair_needed=true
 [[ "$misconfigured" -gt 0 ]] && repair_needed=true
 $restart_needed && repair_needed=true
-$job_inactive && repair_needed=true
 
 echo "Telegraf partition status:"
-print_report
-echo "Default partitions with rows: $stranded"
-echo "pg_cron metadata database: $(sanitise <<<"${cron_db:-unset}")"
-[[ "$cron_db" == postgres ]] \
-  || echo "pg_cron metadata database is $(sanitise <<<"${cron_db:-unset}"); not checking the maintenance job."
+psql_tg -c "$REPORT"
+echo "Rows stranded in default partitions: $stranded"
+echo "pg_cron metadata database: ${cron_db:-unset}"
 echo "pg_cron launcher running: $([[ "$launcher" -gt 0 ]] && echo yes || echo no)"
 echo "Last $JOB_NAME run: $last_run"
 echo
 
 if ! $repair_needed; then
   echo "Telegraf partitions are healthy. Nothing to do."
-  finish 0
+  exit 0
 fi
 
 if $CHECK_ONLY; then
   echo "Repair is needed:"
-  [[ "$stranded" -gt 0 ]]    && echo "  * $stranded default partition(s) hold rows"
+  [[ "$stranded" -gt 0 ]]    && echo "  * $stranded row(s) stranded in default partitions"
   [[ "$behind" -gt 0 ]]      && echo "  * $behind parent(s) with no partition for the current window"
   [[ "$misconfigured" -gt 0 ]] && echo "  * $misconfigured parent(s) with stale partman settings"
   $restart_needed            && echo "  * pg_cron's launcher is dead; maintenance is not running at all"
-  $job_inactive              && echo "  * the maintenance job is missing or inactive"
   echo
   echo "Re-run without --check to repair."
-  finish 1
+  exit 1
 fi
 
 if [[ "$stranded" -gt 0 ]] && ! $ASSUME_YES; then
-  echo "This will permanently discard the rows in the $stranded default partition(s) above."
+  echo "This will permanently discard the $stranded stranded row(s) above."
   $restart_needed && ! $NO_RESTART && \
     echo "so-postgres will also be restarted, which briefly interrupts SOC."
-  [[ -t 0 ]] || { echo "Not a terminal; re-run with --yes to confirm." >&2; finish 1; }
+  [[ -t 0 ]] || { echo "Not a terminal; re-run with --yes to confirm." >&2; exit 2; }
   read -r -p "Continue? [y/N] " answer
-  [[ "$answer" =~ ^[Yy]$ ]] || { echo "Aborted."; finish 0; }
-fi
-
-ERR_STATUS=1
-ERR_PREFIX="Telegraf partition repair failed"
-
-if [[ "$cron_db" == postgres ]]; then
-  if [[ -z "$job" ]]; then
-    echo "Could not register the maintenance job; run a highstate and try again." >&2
-    finish 3
-  fi
-  job_id=${job%%|*}
-  [[ "${job##*|}" == t ]] && restore_active=true || restore_active=false
-  echo "Pausing the $JOB_NAME job during the repair."
-  psql_cron -tAc "SELECT cron.alter_job($job_id, active := false)" >/dev/null
+  [[ "$answer" =~ ^[Yy]$ ]] || { echo "Aborted."; exit 0; }
 fi
 
 if [[ "$misconfigured" -gt 0 ]]; then
@@ -313,24 +186,27 @@ if [[ "$stranded" -gt 0 ]]; then
   # One transaction: Telegraf is still writing, so a default emptied without
   # its partition in place is refilled before maintenance can attach one.
   psql_tg -v ON_ERROR_STOP=1 <<'EOSQL'
-BEGIN;
 DO $$
 DECLARE
     r record;
 BEGIN
     FOR r IN
-        SELECT pc.parent_table, d.default_part
-        FROM so_admin.telegraf_defaults() d
-        JOIN partman.part_config pc ON to_regclass(pc.parent_table) = d.parent_table
-        WHERE d.default_part IS NOT NULL
+        SELECT pc.parent_table,
+               format('%I.%I', n.nspname, c.relname) AS default_table
+        FROM partman.part_config pc
+        JOIN pg_class p ON p.oid = pc.parent_table::regclass
+        JOIN pg_inherits i ON i.inhparent = p.oid
+        JOIN pg_class c ON c.oid = i.inhrelid
+        JOIN pg_namespace n ON n.oid = c.relnamespace
+        WHERE pc.parent_table LIKE 'telegraf.%'
+          AND pg_get_expr(c.relpartbound, c.oid) = 'DEFAULT'
     LOOP
-        EXECUTE format('TRUNCATE TABLE %s', r.default_part);
+        EXECUTE format('TRUNCATE TABLE %s', r.default_table);
         PERFORM partman.create_partition_time(
             r.parent_table, ARRAY[date_trunc('day', now())]::timestamptz[]);
     END LOOP;
 END
 $$;
-COMMIT;
 EOSQL
 fi
 
@@ -346,7 +222,7 @@ if $restart_needed; then
       sleep 2
     done
     docker exec so-postgres pg_isready -U postgres -q \
-      || { echo "so-postgres did not come back; check 'docker logs so-postgres'." >&2; finish 1; }
+      || { echo "so-postgres did not come back; check 'docker logs so-postgres'." >&2; exit 1; }
   fi
 fi
 
@@ -362,14 +238,8 @@ CALL partman.run_maintenance_proc();
 \endif
 EOSQL
 
-if [[ -n "$job_id" ]]; then
-  psql_cron -tAc "SELECT cron.alter_job($job_id, active := true)" >/dev/null
-  restore_active=
-  echo "The $JOB_NAME job is active."
-fi
-
 echo
 echo "Telegraf partition status after repair:"
-print_report
+psql_tg -c "$REPORT"
 echo "The $JOB_NAME job runs hourly at :17. Confirm it fired with:"
 echo "  so-telegraf-repair --check"

salt/redis/config.sls

@@ -50,16 +50,16 @@ redis_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://redis/tools/sbin
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939
     - file_mode: 755
 
 redis_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://redis/tools/sbin_jinja
-    - user: root
-    - group: root
+    - user: 939
+    - group: 939 
     - file_mode: 755
     - template: jinja