From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Alexei Starovoitov <ast@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH 4.16 110/110] bpf: Prevent memory disambiguation attack
Date: Mon, 21 May 2018 23:12:47 +0200 [thread overview]
Message-ID: <20180521210515.145840770@linuxfoundation.org> (raw)
In-Reply-To: <20180521210503.823249477@linuxfoundation.org>
4.16-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alexei Starovoitov <ast@kernel.org>
commit af86ca4e3088fe5eacf2f7e58c01fa68ca067672 upstream
Detect code patterns where malicious 'speculative store bypass' can be used
and sanitize such patterns.
39: (bf) r3 = r10
40: (07) r3 += -216
41: (79) r8 = *(u64 *)(r7 +0) // slow read
42: (7a) *(u64 *)(r10 -72) = 0 // verifier inserts this instruction
43: (7b) *(u64 *)(r8 +0) = r3 // this store becomes slow due to r8
44: (79) r1 = *(u64 *)(r6 +0) // cpu speculatively executes this load
45: (71) r2 = *(u8 *)(r1 +0) // speculatively arbitrary 'load byte'
// is now sanitized
Above code after x86 JIT becomes:
e5: mov %rbp,%rdx
e8: add $0xffffffffffffff28,%rdx
ef: mov 0x0(%r13),%r14
f3: movq $0x0,-0x48(%rbp)
fb: mov %rdx,0x0(%r14)
ff: mov 0x0(%rbx),%rdi
103: movzbq 0x0(%rdi),%rsi
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
include/linux/bpf_verifier.h | 1
kernel/bpf/verifier.c | 59 ++++++++++++++++++++++++++++++++++++++++---
2 files changed, 57 insertions(+), 3 deletions(-)
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -146,6 +146,7 @@ struct bpf_insn_aux_data {
s32 call_imm; /* saved imm field of call insn */
};
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
+ int sanitize_stack_off; /* stack slot to be cleared */
bool seen; /* this insn was processed by the verifier */
};
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -970,7 +970,7 @@ static bool register_is_null(struct bpf_
*/
static int check_stack_write(struct bpf_verifier_env *env,
struct bpf_func_state *state, /* func where register points to */
- int off, int size, int value_regno)
+ int off, int size, int value_regno, int insn_idx)
{
struct bpf_func_state *cur; /* state of the current function */
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
@@ -1009,8 +1009,33 @@ static int check_stack_write(struct bpf_
state->stack[spi].spilled_ptr = cur->regs[value_regno];
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
- for (i = 0; i < BPF_REG_SIZE; i++)
+ for (i = 0; i < BPF_REG_SIZE; i++) {
+ if (state->stack[spi].slot_type[i] == STACK_MISC &&
+ !env->allow_ptr_leaks) {
+ int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
+ int soff = (-spi - 1) * BPF_REG_SIZE;
+
+ /* detected reuse of integer stack slot with a pointer
+ * which means either llvm is reusing stack slot or
+ * an attacker is trying to exploit CVE-2018-3639
+ * (speculative store bypass)
+ * Have to sanitize that slot with preemptive
+ * store of zero.
+ */
+ if (*poff && *poff != soff) {
+ /* disallow programs where single insn stores
+ * into two different stack slots, since verifier
+ * cannot sanitize them
+ */
+ verbose(env,
+ "insn %d cannot access two stack slots fp%d and fp%d",
+ insn_idx, *poff, soff);
+ return -EINVAL;
+ }
+ *poff = soff;
+ }
state->stack[spi].slot_type[i] = STACK_SPILL;
+ }
} else {
u8 type = STACK_MISC;
@@ -1685,7 +1710,7 @@ static int check_mem_access(struct bpf_v
if (t == BPF_WRITE)
err = check_stack_write(env, state, off, size,
- value_regno);
+ value_regno, insn_idx);
else
err = check_stack_read(env, state, off, size,
value_regno);
@@ -5156,6 +5181,34 @@ static int convert_ctx_accesses(struct b
else
continue;
+ if (type == BPF_WRITE &&
+ env->insn_aux_data[i + delta].sanitize_stack_off) {
+ struct bpf_insn patch[] = {
+ /* Sanitize suspicious stack slot with zero.
+ * There are no memory dependencies for this store,
+ * since it's only using frame pointer and immediate
+ * constant of zero
+ */
+ BPF_ST_MEM(BPF_DW, BPF_REG_FP,
+ env->insn_aux_data[i + delta].sanitize_stack_off,
+ 0),
+ /* the original STX instruction will immediately
+ * overwrite the same stack slot with appropriate value
+ */
+ *insn,
+ };
+
+ cnt = ARRAY_SIZE(patch);
+ new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
continue;
next prev parent reply other threads:[~2018-05-21 21:26 UTC|newest]
Thread overview: 120+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-21 21:10 [PATCH 4.16 000/110] 4.16.11-stable review Greg Kroah-Hartman
2018-05-21 21:10 ` [PATCH 4.16 001/110] xhci: Fix USB3 NULL pointer dereference at logical disconnect Greg Kroah-Hartman
2018-05-21 21:10 ` [PATCH 4.16 002/110] usbip: usbip_host: refine probe and disconnect debug msgs to be useful Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 003/110] usbip: usbip_host: delete device from busid_table after rebind Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 004/110] usbip: usbip_host: run rebind from exit when module is removed Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 005/110] usbip: usbip_host: fix NULL-ptr deref and use-after-free errors Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 006/110] usbip: usbip_host: fix bad unlock balance during stub_probe() Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 007/110] ALSA: usb: mixer: volume quirk for CM102-A+/102S+ Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 008/110] ALSA: hda/realtek - Clevo P950ER ALC1220 Fixup Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 009/110] ALSA: hda: Add Lenovo C50 All in one to the power_save blacklist Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 010/110] ALSA: control: fix a redundant-copy issue Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 011/110] spi: pxa2xx: Allow 64-bit DMA Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 012/110] spi: bcm-qspi: Avoid setting MSPI_CDRAM_PCS for spi-nor master Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 013/110] spi: bcm-qspi: Always read and set BSPI_MAST_N_BOOT_CTRL Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 015/110] KVM: arm/arm64: Properly protect VGIC locks from IRQs Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 016/110] KVM: arm/arm64: VGIC/ITS: Promote irq_lock() in update_affinity Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 017/110] KVM: arm/arm64: VGIC/ITS save/restore: protect kvm_read_guest() calls Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 018/110] KVM: arm/arm64: VGIC/ITS: protect kvm_read_guest() calls with SRCU lock Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 019/110] hwmon: (k10temp) Fix reading critical temperature register Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 020/110] hwmon: (k10temp) Use API function to access System Management Network Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 021/110] vfio: ccw: fix cleanup if cp_prefetch fails Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 022/110] tracing/x86/xen: Remove zero data size trace events trace_xen_mmu_flush_tlb{_all} Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 023/110] vsprintf: Replace memory barrier with static_key for random_ptr_key update Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 024/110] x86/amd_nb: Add support for Raven Ridge CPUs Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 025/110] tee: shm: fix use-after-free via temporarily dropped reference Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 026/110] netfilter: nf_tables: free set name in error path Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 027/110] netfilter: nf_tables: cant fail after linking rule into active rule list Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 028/110] netfilter: nf_tables: nf_tables_obj_lookup_byhandle() can be static Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 029/110] ARM64: dts: marvell: armada-cp110: Add clocks for the xmdio node Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 030/110] ARM64: dts: marvell: armada-cp110: Add mg_core_clk for ethernet node Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 031/110] i2c: designware: fix poll-after-enable regression Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 032/110] mtd: rawnand: marvell: Fix read logic for layouts with ->nchunks > 2 Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 033/110] powerpc/powernv: Fix NVRAM sleep in invalid context when crashing Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 034/110] drm: Match sysfs name in link removal to link creation Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 035/110] cpufreq: armada-37xx: driver relies on cpufreq-dt Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 036/110] lib/test_bitmap.c: fix bitmap optimisation tests to report errors correctly Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 037/110] radix tree: fix multi-order iteration race Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 038/110] mm: dont allow deferred pages with NEED_PER_CPU_KM Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 039/110] drm/i915/gen9: Add WaClearHIZ_WM_CHICKEN3 for bxt and glk Greg Kroah-Hartman
2018-05-22 8:09 ` [Mesa-dev] " Martin Peres
2018-05-22 9:27 ` Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 040/110] s390/qdio: fix access to uninitialized qdio_q fields Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 041/110] s390/cpum_sf: ensure sample frequency of perf event attributes is non-zero Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 042/110] s390/qdio: dont release memory in qdio_setup_irq() Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 043/110] s390: remove indirect branch from do_softirq_own_stack Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 044/110] bcache: return 0 from bch_debug_init() if CONFIG_DEBUG_FS=n Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 045/110] x86/pkeys: Override pkey when moving away from PROT_EXEC Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 046/110] x86/pkeys: Do not special case protection key 0 Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 047/110] efi: Avoid potential crashes, fix the struct efi_pci_io_protocol_32 definition for mixed mode Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 048/110] ARM: 8771/1: kprobes: Prohibit kprobes on do_undefinstr Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 049/110] x86/apic/x2apic: Initialize cluster ID properly Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 050/110] x86/mm: Drop TS_COMPAT on 64-bit exec() syscall Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 051/110] tick/broadcast: Use for_each_cpu() specially on UP kernels Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 052/110] ARM: 8769/1: kprobes: Fix to use get_kprobe_ctlblk after irq-disabed Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 053/110] ARM: 8770/1: kprobes: Prohibit probing on optimized_callback Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 054/110] ARM: 8772/1: kprobes: Prohibit kprobes on get_user functions Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 055/110] Btrfs: fix xattr loss after power failure Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 056/110] Btrfs: send, fix invalid access to commit roots due to concurrent snapshotting Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 057/110] btrfs: property: Set incompat flag if lzo/zstd compression is set Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 058/110] btrfs: fix crash when trying to resume balance without the resume flag Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 059/110] btrfs: Split btrfs_del_delalloc_inode into 2 functions Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 060/110] btrfs: Fix delalloc inodes invalidation during transaction abort Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 061/110] btrfs: fix reading stale metadata blocks after degraded raid1 mounts Greg Kroah-Hartman
2018-05-21 21:11 ` [PATCH 4.16 062/110] x86/nospec: Simplify alternative_msr_write() Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 063/110] x86/bugs: Concentrate bug detection into a separate function Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 064/110] x86/bugs: Concentrate bug reporting " Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 065/110] x86/bugs: Read SPEC_CTRL MSR during boot and re-use reserved bits Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 066/110] x86/bugs, KVM: Support the combination of guest and host IBRS Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 067/110] x86/bugs: Expose /sys/../spec_store_bypass Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 068/110] x86/cpufeatures: Add X86_FEATURE_RDS Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 069/110] x86/bugs: Provide boot parameters for the spec_store_bypass_disable mitigation Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 070/110] x86/bugs/intel: Set proper CPU features and setup RDS Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 071/110] x86/bugs: Whitelist allowed SPEC_CTRL MSR values Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 072/110] x86/bugs/AMD: Add support to disable RDS on Fam[15,16,17]h if requested Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 073/110] x86/KVM/VMX: Expose SPEC_CTRL Bit(2) to the guest Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 074/110] x86/speculation: Create spec-ctrl.h to avoid include hell Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 075/110] prctl: Add speculation control prctls Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 076/110] x86/process: Allow runtime control of Speculative Store Bypass Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 077/110] x86/speculation: Add prctl for Speculative Store Bypass mitigation Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 078/110] nospec: Allow getting/setting on non-current task Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 079/110] proc: Provide details on speculation flaw mitigations Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 080/110] seccomp: Enable " Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 081/110] x86/bugs: Make boot modes __ro_after_init Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 082/110] prctl: Add force disable speculation Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 083/110] seccomp: Use PR_SPEC_FORCE_DISABLE Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 084/110] seccomp: Add filter flag to opt-out of SSB mitigation Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 085/110] seccomp: Move speculation migitation control to arch code Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 086/110] x86/speculation: Make "seccomp" the default mode for Speculative Store Bypass Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 087/110] x86/bugs: Rename _RDS to _SSBD Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 088/110] proc: Use underscores for SSBD in status Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 089/110] Documentation/spec_ctrl: Do some minor cleanups Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 090/110] x86/bugs: Fix __ssb_select_mitigation() return type Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 091/110] x86/bugs: Make cpu_show_common() static Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 092/110] x86/bugs: Fix the parameters alignment and missing void Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 093/110] x86/cpu: Make alternative_msr_write work for 32-bit code Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 094/110] KVM: SVM: Move spec control call after restore of GS Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 096/110] x86/cpufeatures: Disentangle MSR_SPEC_CTRL enumeration from IBRS Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 097/110] x86/cpufeatures: Disentangle SSBD enumeration Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 098/110] x86/cpufeatures: Add FEATURE_ZEN Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 099/110] x86/speculation: Handle HT correctly on AMD Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 100/110] x86/bugs, KVM: Extend speculation control for VIRT_SPEC_CTRL Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 101/110] x86/speculation: Add virtualized speculative store bypass disable support Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 102/110] x86/speculation: Rework speculative_store_bypass_update() Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 103/110] x86/bugs: Unify x86_spec_ctrl_{set_guest,restore_host} Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 104/110] x86/bugs: Expose x86_spec_ctrl_base directly Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 105/110] x86/bugs: Remove x86_spec_ctrl_set() Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 106/110] x86/bugs: Rework spec_ctrl base and mask logic Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 107/110] x86/speculation, KVM: Implement support for VIRT_SPEC_CTRL/LS_CFG Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 108/110] KVM: SVM: Implement VIRT_SPEC_CTRL support for SSBD Greg Kroah-Hartman
2018-05-21 21:12 ` [PATCH 4.16 109/110] x86/bugs: Rename SSBD_NO to SSB_NO Greg Kroah-Hartman
2018-05-21 21:12 ` Greg Kroah-Hartman [this message]
2018-05-22 10:48 ` [PATCH 4.16 000/110] 4.16.11-stable review Naresh Kamboju
2018-05-22 12:54 ` Dan Rue
2018-05-22 14:02 ` Greg Kroah-Hartman
2018-05-22 14:22 ` Dan Rue
2018-05-22 14:02 ` Greg Kroah-Hartman
2018-05-22 13:35 ` Guenter Roeck
2018-05-22 17:46 ` Greg Kroah-Hartman
2018-05-22 20:45 ` Shuah Khan
2018-05-23 6:01 ` Greg Kroah-Hartman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180521210515.145840770@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=ast@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).