kernel.git/arch/arm64/net, branch linux-4.11.y

bpf, arm64: fix faulty emission of map access in tail calls

2017-06-07T10:09:59Z

[ Upstream commit d8b54110ee944de522ccd3531191f39986ec20f9 ] Shubham was recently asking on netdev why in arm64 JIT we don't multiply the index for accessing the tail call map by 8. That led me into testing out arm64 JIT wrt tail calls and it turned out I got a NULL pointer dereference on the tail call. The buggy access is at: prog = array->ptrs[index]; if (prog == NULL) goto out; [...] 00000060: d2800e0a mov x10, #0x70 // #112 00000064: f86a682a ldr x10, [x1,x10] 00000068: f862694b ldr x11, [x10,x2] 0000006c: b40000ab cbz x11, 0x00000080 [...] The code triggering the crash is f862694b. x1 at the time contains the address of the bpf array, x10 offsetof(struct bpf_array, ptrs). Meaning, above we load the pointer to the program at map slot 0 into x10. x10 can then be NULL if the slot is not occupied, which we later on try to access with a user given offset in x2 that is the map index. Fix this by emitting the following instead: [...] 00000060: d2800e0a mov x10, #0x70 // #112 00000064: 8b0a002a add x10, x1, x10 00000068: d37df04b lsl x11, x2, #3 0000006c: f86b694b ldr x11, [x10,x11] 00000070: b40000ab cbz x11, 0x00000084 [...] This basically adds the offset to ptrs to the base address of the bpf array we got and we later on access the map with an index * 8 offset relative to that. The tail call map itself is basically one large area with meta data at the head followed by the array of prog pointers. This makes tail calls working again, tested on Cavium ThunderX ARMv8. Fixes: ddb55992b04d ("arm64: bpf: implement bpf_tail_call() helper") Reported-by: Shubham Bansal Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman

bpf, arm64: fix jit branch offset related to ldimm64

2017-05-14T12:06:01Z

[ Upstream commit ddc665a4bb4b728b4e6ecec8db1b64efa9184b9c ] When the instruction right before the branch destination is a 64 bit load immediate, we currently calculate the wrong jump offset in the ctx->offset[] array as we only account one instruction slot for the 64 bit load immediate although it uses two BPF instructions. Fix it up by setting the offset into the right slot after we incremented the index. Before (ldimm64 test 1): [...] 00000020: 52800007 mov w7, #0x0 // #0 00000024: d2800060 mov x0, #0x3 // #3 00000028: d2800041 mov x1, #0x2 // #2 0000002c: eb01001f cmp x0, x1 00000030: 54ffff82 b.cs 0x00000020 00000034: d29fffe7 mov x7, #0xffff // #65535 00000038: f2bfffe7 movk x7, #0xffff, lsl #16 0000003c: f2dfffe7 movk x7, #0xffff, lsl #32 00000040: f2ffffe7 movk x7, #0xffff, lsl #48 00000044: d29dddc7 mov x7, #0xeeee // #61166 00000048: f2bdddc7 movk x7, #0xeeee, lsl #16 0000004c: f2ddddc7 movk x7, #0xeeee, lsl #32 00000050: f2fdddc7 movk x7, #0xeeee, lsl #48 [...] After (ldimm64 test 1): [...] 00000020: 52800007 mov w7, #0x0 // #0 00000024: d2800060 mov x0, #0x3 // #3 00000028: d2800041 mov x1, #0x2 // #2 0000002c: eb01001f cmp x0, x1 00000030: 540000a2 b.cs 0x00000044 00000034: d29fffe7 mov x7, #0xffff // #65535 00000038: f2bfffe7 movk x7, #0xffff, lsl #16 0000003c: f2dfffe7 movk x7, #0xffff, lsl #32 00000040: f2ffffe7 movk x7, #0xffff, lsl #48 00000044: d29dddc7 mov x7, #0xeeee // #61166 00000048: f2bdddc7 movk x7, #0xeeee, lsl #16 0000004c: f2ddddc7 movk x7, #0xeeee, lsl #32 00000050: f2fdddc7 movk x7, #0xeeee, lsl #48 [...] Also, add a couple of test cases to make sure JITs pass this test. Tested on Cavium ThunderX ARMv8. The added test cases all pass after the fix. Fixes: 8eee539ddea0 ("arm64: bpf: fix out-of-bounds read in bpf2a64_offset()") Reported-by: David S. Miller Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Cc: Xi Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman

bpf: fix unlocking of jited image when module ronx not set

2017-02-21T18:30:14Z

Eric and Willem reported that they recently saw random crashes when JIT was in use and bisected this to 74451e66d516 ("bpf: make jited programs visible in traces"). Issue was that the consolidation part added bpf_jit_binary_unlock_ro() that would unlock previously made read-only memory back to read-write. However, DEBUG_SET_MODULE_RONX cannot be used for this to test for presence of set_memory_*() functions. We need to use ARCH_HAS_SET_MEMORY instead to fix this; also add the corresponding bpf_jit_binary_lock_ro() to filter.h. Fixes: 74451e66d516 ("bpf: make jited programs visible in traces") Reported-by: Eric Dumazet Reported-by: Willem de Bruijn Bisected-by: Eric Dumazet Signed-off-by: Daniel Borkmann Tested-by: Willem de Bruijn Signed-off-by: David S. Miller

bpf: make jited programs visible in traces

2017-02-17T18:40:05Z

Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller

bpf: remove stubs for cBPF from arch code

2017-02-17T18:40:04Z

Remove the dummy bpf_jit_compile() stubs for eBPF JITs and make that a single __weak function in the core that can be overridden similarly to the eBPF one. Also remove stale pr_err() mentions of bpf_jit_compile. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller

arm64: bpf: optimize LD_ABS, LD_IND

2016-06-11T06:11:50Z

Remove superfluous stack frame, saving us 3 instructions for every LD_ABS or LD_IND. Signed-off-by: Zi Shen Lim Signed-off-by: David S. Miller

arm64: bpf: optimize JMP_CALL

2016-06-11T06:11:50Z

Remove superfluous stack frame, saving us 3 instructions for every JMP_CALL. Signed-off-by: Zi Shen Lim Signed-off-by: David S. Miller

arm64: bpf: implement bpf_tail_call() helper

2016-06-11T06:11:49Z

Add support for JMP_CALL_X (tail call) introduced by commit 04fd61ab36ec ("bpf: allow bpf programs to tail-call other bpf programs"). bpf_tail_call() arguments: ctx - context pointer passed to next program array - pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY index - index inside array that selects specific program to run In this implementation arm64 JIT jumps into callee program after prologue, so callee program reuses the same stack. For tail_call_cnt, we use the callee-saved R26 (which was already saved/restored but previously unused by JIT). With this patch a tail call generates the following code on arm64: if (index >= array->map.max_entries) goto out; 34: mov x10, #0x10 // #16 38: ldr w10, [x1,x10] 3c: cmp w2, w10 40: b.ge 0x0000000000000074 if (tail_call_cnt > MAX_TAIL_CALL_CNT) goto out; tail_call_cnt++; 44: mov x10, #0x20 // #32 48: cmp x26, x10 4c: b.gt 0x0000000000000074 50: add x26, x26, #0x1 prog = array->ptrs[index]; if (prog == NULL) goto out; 54: mov x10, #0x68 // #104 58: ldr x10, [x1,x10] 5c: ldr x11, [x10,x2] 60: cbz x11, 0x0000000000000074 goto *(prog->bpf_func + prologue_size); 64: mov x10, #0x20 // #32 68: ldr x10, [x11,x10] 6c: add x10, x10, #0x20 70: br x10 74: Signed-off-by: Zi Shen Lim Signed-off-by: David S. Miller

bpf: arm64: remove callee-save registers use for tmp registers

2016-05-17T18:03:33Z

In the current implementation of ARM64 eBPF JIT, R23 and R24 are used for tmp registers, which are callee-saved registers. This leads to variable size of JIT prologue and epilogue. The latest blinding constant change prefers to constant size of prologue and epilogue. AAPCS reserves R9 ~ R15 for temp registers which not need to be saved/restored during function call. So, replace R23 and R24 to R10 and R11, and remove tmp_used flag to save 2 instructions for some jited BPF program. CC: Daniel Borkmann Acked-by: Zi Shen Lim Signed-off-by: Yang Shi Acked-by: Catalin Marinas Acked-by: Daniel Borkmann Signed-off-by: David S. Miller

bpf, arm64: add support for constant blinding

2016-05-16T17:49:33Z

This patch adds recently added constant blinding helpers into the arm64 eBPF JIT. In the bpf_int_jit_compile() path, requirements are to utilize bpf_jit_blind_constants()/bpf_jit_prog_release_other() pair for rewriting the program into a blinded one, and to map the BPF_REG_AX register to a CPU register. The mapping is on x9. Signed-off-by: Daniel Borkmann Acked-by: Zi Shen Lim Acked-by: Yang Shi Tested-by: Yang Shi Signed-off-by: David S. Miller