Give the static TLS block enough headroom for libgomp

tox.ini

@@ -29,6 +29,25 @@ passenv =
     OMP_NUM_THREADS
     PATH
     LD_LIBRARY_PATH
+# Work around Qiskit/qiskit#17213: with qiskit 2.6.0 installed, importing our
+# extension fails on Linux with "cannot allocate memory in static TLS block".
+#
+# glibc sizes the per-thread TLS block at startup and keeps only a small surplus for
+# libraries dlopen'ed afterwards that need initial-exec TLS. Every Python extension
+# arrives that way, so they all draw on that surplus. qiskit 2.6.0's _accelerate grew
+# from 736 to 1544 bytes of it (matrixmultiply 0.3.11 enabling AVX-512 kernels, which
+# quadruple one thread-local buffer), which leaves too little for the libgomp our
+# extension pulls in. The error names libgomp, but it is whoever asks last that fails.
+#
+# Raising the surplus restores the headroom. It is reserved per thread and only commits
+# the pages actually used, so a generous value costs little. Drop this once 17213 is
+# fixed upstream.
+#
+# Linux-only: this is a glibc mechanism, and macOS links libomp with no equivalent
+# limit. Note glibc silently ignores an unrecognized tunable name, so a typo here looks
+# like a working config.
+setenv =
+    linux: GLIBC_TUNABLES = glibc.rtld.optional_static_tls=65536
 extras =
     test
 commands =
@@ -52,6 +71,9 @@ allowlist_externals =
     mpirun
 setenv =
     SBD_TEST_NPROCS = {env:SBD_TEST_NPROCS:2}
+    # setenv is replaced, not merged, in a child environment, so repeat the
+    # static-TLS headroom [testenv] sets; see the comment there.
+    linux: GLIBC_TUNABLES = glibc.rtld.optional_static_tls=65536
 commands =
     mpirun -n {env:SBD_TEST_NPROCS} pytest --only-mpi {posargs}