summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-16 12:47:46 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-16 12:47:46 -0800
commit5b0e2cb020085efe202123162502e0b551e49a0e (patch)
tree534bbb4c9f98c2ed9a520e11107029e5df38c3c2 /arch/powerpc/net
parent758f875848d78148cf9a9cdb3ff1ddf29b234056 (diff)
parent3ffa9d9e2a7c10127d8cbf91ea2be15390b450ed (diff)
downloadlinux-5b0e2cb020085efe202123162502e0b551e49a0e.tar.gz
linux-5b0e2cb020085efe202123162502e0b551e49a0e.tar.bz2
linux-5b0e2cb020085efe202123162502e0b551e49a0e.zip
Merge tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman: "A bit of a small release, I suspect in part due to me travelling for KS. But my backlog of patches to review is smaller than usual, so I think in part folks just didn't send as much this cycle. Non-highlights: - Five fixes for the >128T address space handling, both to fix bugs in our implementation and to bring the semantics exactly into line with x86. Highlights: - Support for a new OPAL call on bare metal machines which gives us a true NMI (ie. is not masked by MSR[EE]=0) for debugging etc. - Support for Power9 DD2 in the CXL driver. - Improvements to machine check handling so that uncorrectable errors can be reported into the generic memory_failure() machinery. - Some fixes and improvements for VPHN, which is used under PowerVM to notify the Linux partition of topology changes. - Plumbing to enable TM (transactional memory) without suspend on some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND). - Support for emulating vector loads form cache-inhibited memory, on some Power9 revisions. - Disable the fast-endian switch "syscall" by default (behind a CONFIG), we believe it has never had any users. - A major rework of the API drivers use when initiating and waiting for long running operations performed by OPAL firmware, and changes to the powernv_flash driver to use the new API. - Several fixes for the handling of FP/VMX/VSX while processes are using transactional memory. - Optimisations of TLB range flushes when using the radix MMU on Power9. - Improvements to the VAS facility used to access coprocessors on Power9, and related improvements to the way the NX crypto driver handles requests. - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit. Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard, Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley, Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu, Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee, Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A. Kennington III" * tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits) powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature powerpc/64s: Fix masking of SRR1 bits on instruction fault powerpc/64s: mm_context.addr_limit is only used on hash powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary powerpc/64s/hash: Fix fork() with 512TB process address space powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation powerpc/64s/hash: Fix 512T hint detection to use >= 128T powerpc: Fix DABR match on hash based systems powerpc/signal: Properly handle return value from uprobe_deny_signal() powerpc/fadump: use kstrtoint to handle sysfs store powerpc/lib: Implement UACCESS_FLUSHCACHE API powerpc/lib: Implement PMEM API powerpc/powernv/npu: Don't explicitly flush nmmu tlb powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm() powerpc/powernv/idle: Round up latency and residency values powerpc/kprobes: refactor kprobe_lookup_name for safer string operations powerpc/kprobes: Blacklist emulate_update_regs() from kprobes powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace powerpc/kprobes: Disable preemption before invoking probe handler for optprobes ...
Diffstat (limited to 'arch/powerpc/net')
-rw-r--r--arch/powerpc/net/bpf_jit64.h7
-rw-r--r--arch/powerpc/net/bpf_jit_comp64.c16
2 files changed, 14 insertions, 9 deletions
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index 62fa7589db2b..8bdef7ed28a8 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -23,7 +23,7 @@
* [ nv gpr save area ] 8*8 |
* [ tail_call_cnt ] 8 |
* [ local_tmp_var ] 8 |
- * fp (r31) --> [ ebpf stack space ] 512 |
+ * fp (r31) --> [ ebpf stack space ] upto 512 |
* [ frame header ] 32/112 |
* sp (r1) ---> [ stack pointer ] --------------
*/
@@ -32,8 +32,8 @@
#define BPF_PPC_STACK_SAVE (8*8)
/* for bpf JIT code internal usage */
#define BPF_PPC_STACK_LOCALS 16
-/* Ensure this is quadword aligned */
-#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + MAX_BPF_STACK + \
+/* stack frame excluding BPF stack, ensure this is quadword aligned */
+#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \
BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
#ifndef __ASSEMBLY__
@@ -103,6 +103,7 @@ struct codegen_context {
*/
unsigned int seen;
unsigned int idx;
+ unsigned int stack_size;
};
#endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index a66e64b0b251..46d74e81aff1 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -69,7 +69,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
static int bpf_jit_stack_local(struct codegen_context *ctx)
{
if (bpf_has_stack_frame(ctx))
- return STACK_FRAME_MIN_SIZE + MAX_BPF_STACK;
+ return STACK_FRAME_MIN_SIZE + ctx->stack_size;
else
return -(BPF_PPC_STACK_SAVE + 16);
}
@@ -82,8 +82,9 @@ static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx)
static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
{
if (reg >= BPF_PPC_NVR_MIN && reg < 32)
- return (bpf_has_stack_frame(ctx) ? BPF_PPC_STACKFRAME : 0)
- - (8 * (32 - reg));
+ return (bpf_has_stack_frame(ctx) ?
+ (BPF_PPC_STACKFRAME + ctx->stack_size) : 0)
+ - (8 * (32 - reg));
pr_err("BPF JIT is asking about unknown registers");
BUG();
@@ -134,7 +135,7 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
PPC_BPF_STL(0, 1, PPC_LR_STKOFF);
}
- PPC_BPF_STLU(1, 1, -BPF_PPC_STACKFRAME);
+ PPC_BPF_STLU(1, 1, -(BPF_PPC_STACKFRAME + ctx->stack_size));
}
/*
@@ -161,7 +162,7 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
/* Setup frame pointer to point to the bpf stack area */
if (bpf_is_seen_register(ctx, BPF_REG_FP))
PPC_ADDI(b2p[BPF_REG_FP], 1,
- STACK_FRAME_MIN_SIZE + MAX_BPF_STACK);
+ STACK_FRAME_MIN_SIZE + ctx->stack_size);
}
static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx)
@@ -183,7 +184,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
/* Tear down our stack frame */
if (bpf_has_stack_frame(ctx)) {
- PPC_ADDI(1, 1, BPF_PPC_STACKFRAME);
+ PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
if (ctx->seen & SEEN_FUNC) {
PPC_BPF_LL(0, 1, PPC_LR_STKOFF);
PPC_MTLR(0);
@@ -1013,6 +1014,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
memset(&cgctx, 0, sizeof(struct codegen_context));
+ /* Make sure that the stack is quadword aligned. */
+ cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
+
/* Scouting faux-generate pass 0 */
if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) {
/* We hit something illegal or unsupported. */