diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-25 12:39:01 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-25 12:39:01 -0700 |
commit | df45da57cbd35715d590a36a12968a94508ccd1f (patch) | |
tree | f001218ffbd01d42f829be275df5542b1b454f2d /arch/arm64/kernel/entry-ftrace.S | |
parent | 53b5e72b9d89853b7e622239676163ede52acffe (diff) | |
parent | eeb3557cc188e42ae7f7bef2d6dc5bf0e078412e (diff) | |
download | lwn-df45da57cbd35715d590a36a12968a94508ccd1f.tar.gz lwn-df45da57cbd35715d590a36a12968a94508ccd1f.zip |
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Will Deacon:
"ACPI:
- Improve error reporting when failing to manage SDEI on AGDI device
removal
Assembly routines:
- Improve register constraints so that the compiler can make use of
the zero register instead of moving an immediate #0 into a GPR
- Allow the compiler to allocate the registers used for CAS
instructions
CPU features and system registers:
- Cleanups to the way in which CPU features are identified from the
ID register fields
- Extend system register definition generation to handle Enum types
when defining shared register fields
- Generate definitions for new _EL2 registers and add new fields for
ID_AA64PFR1_EL1
- Allow SVE to be disabled separately from SME on the kernel
command-line
Tracing:
- Support for "direct calls" in ftrace, which enables BPF tracing for
arm64
Kdump:
- Don't bother unmapping the crashkernel from the linear mapping,
which then allows us to use huge (block) mappings and reduce TLB
pressure when a crashkernel is loaded.
Memory management:
- Try again to remove data cache invalidation from the coherent DMA
allocation path
- Simplify the fixmap code by mapping at page granularity
- Allow the kfence pool to be allocated early, preventing the rest of
the linear mapping from being forced to page granularity
Perf and PMU:
- Move CPU PMU code out to drivers/perf/ where it can be reused by
the 32-bit ARM architecture when running on ARMv8 CPUs
- Fix race between CPU PMU probing and pKVM host de-privilege
- Add support for Apple M2 CPU PMU
- Adjust the generic PERF_COUNT_HW_BRANCH_INSTRUCTIONS event
dynamically, depending on what the CPU actually supports
- Minor fixes and cleanups to system PMU drivers
Stack tracing:
- Use the XPACLRI instruction to strip PAC from pointers, rather than
rolling our own function in C
- Remove redundant PAC removal for toolchains that handle this in
their builtins
- Make backtracing more resilient in the face of instrumentation
Miscellaneous:
- Fix single-step with KGDB
- Remove harmless warning when 'nokaslr' is passed on the kernel
command-line
- Minor fixes and cleanups across the board"
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (72 commits)
KVM: arm64: Ensure CPU PMU probes before pKVM host de-privilege
arm64: kexec: include reboot.h
arm64: delete dead code in this_cpu_set_vectors()
arm64/cpufeature: Use helper macro to specify ID register for capabilites
drivers/perf: hisi: add NULL check for name
drivers/perf: hisi: Remove redundant initialized of pmu->name
arm64/cpufeature: Consistently use symbolic constants for min_field_value
arm64/cpufeature: Pull out helper for CPUID register definitions
arm64/sysreg: Convert HFGITR_EL2 to automatic generation
ACPI: AGDI: Improve error reporting for problems during .remove()
arm64: kernel: Fix kernel warning when nokaslr is passed to commandline
perf/arm-cmn: Fix port detection for CMN-700
arm64: kgdb: Set PSTATE.SS to 1 to re-enable single-step
arm64: move PAC masks to <asm/pointer_auth.h>
arm64: use XPACLRI to strip PAC
arm64: avoid redundant PAC stripping in __builtin_return_address()
arm64/sme: Fix some comments of ARM SME
arm64/signal: Alloc tpidr2 sigframe after checking system_supports_tpidr2()
arm64/signal: Use system_supports_tpidr2() to check TPIDR2
arm64/idreg: Don't disable SME when disabling SVE
...
Diffstat (limited to 'arch/arm64/kernel/entry-ftrace.S')
-rw-r--r-- | arch/arm64/kernel/entry-ftrace.S | 90 |
1 files changed, 75 insertions, 15 deletions
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 350ed81324ac..1c38a60575aa 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -36,6 +36,31 @@ SYM_CODE_START(ftrace_caller) bti c +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + /* + * The literal pointer to the ops is at an 8-byte aligned boundary + * which is either 12 or 16 bytes before the BL instruction in the call + * site. See ftrace_call_adjust() for details. + * + * Therefore here the LR points at `literal + 16` or `literal + 20`, + * and we can find the address of the literal in either case by + * aligning to an 8-byte boundary and subtracting 16. We do the + * alignment first as this allows us to fold the subtraction into the + * LDR. + */ + bic x11, x30, 0x7 + ldr x11, [x11, #-(4 * AARCH64_INSN_SIZE)] // op + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * If the op has a direct call, handle it immediately without + * saving/restoring registers. + */ + ldr x17, [x11, #FTRACE_OPS_DIRECT_CALL] // op->direct_call + cbnz x17, ftrace_caller_direct +#endif +#endif + /* Save original SP */ mov x10, sp @@ -49,6 +74,10 @@ SYM_CODE_START(ftrace_caller) stp x6, x7, [sp, #FREGS_X6] str x8, [sp, #FREGS_X8] +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + str xzr, [sp, #FREGS_DIRECT_TRAMP] +#endif + /* Save the callsite's FP, LR, SP */ str x29, [sp, #FREGS_FP] str x9, [sp, #FREGS_LR] @@ -71,20 +100,7 @@ SYM_CODE_START(ftrace_caller) mov x3, sp // regs #ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS - /* - * The literal pointer to the ops is at an 8-byte aligned boundary - * which is either 12 or 16 bytes before the BL instruction in the call - * site. See ftrace_call_adjust() for details. - * - * Therefore here the LR points at `literal + 16` or `literal + 20`, - * and we can find the address of the literal in either case by - * aligning to an 8-byte boundary and subtracting 16. We do the - * alignment first as this allows us to fold the subtraction into the - * LDR. - */ - bic x2, x30, 0x7 - ldr x2, [x2, #-16] // op - + mov x2, x11 // op ldr x4, [x2, #FTRACE_OPS_FUNC] // op->func blr x4 // op->func(ip, parent_ip, op, regs) @@ -107,8 +123,15 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) ldp x6, x7, [sp, #FREGS_X6] ldr x8, [sp, #FREGS_X8] - /* Restore the callsite's FP, LR, PC */ + /* Restore the callsite's FP */ ldr x29, [sp, #FREGS_FP] + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + ldr x17, [sp, #FREGS_DIRECT_TRAMP] + cbnz x17, ftrace_caller_direct_late +#endif + + /* Restore the callsite's LR and PC */ ldr x30, [sp, #FREGS_LR] ldr x9, [sp, #FREGS_PC] @@ -116,8 +139,45 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) add sp, sp, #FREGS_SIZE + 32 ret x9 + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_INNER_LABEL(ftrace_caller_direct_late, SYM_L_LOCAL) + /* + * Head to a direct trampoline in x17 after having run other tracers. + * The ftrace_regs are live, and x0-x8 and FP have been restored. The + * LR, PC, and SP have not been restored. + */ + + /* + * Restore the callsite's LR and PC matching the trampoline calling + * convention. + */ + ldr x9, [sp, #FREGS_LR] + ldr x30, [sp, #FREGS_PC] + + /* Restore the callsite's SP */ + add sp, sp, #FREGS_SIZE + 32 + +SYM_INNER_LABEL(ftrace_caller_direct, SYM_L_LOCAL) + /* + * Head to a direct trampoline in x17. + * + * We use `BR X17` as this can safely land on a `BTI C` or `PACIASP` in + * the trampoline, and will not unbalance any return stack. + */ + br x17 +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ SYM_CODE_END(ftrace_caller) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_CODE_START(ftrace_stub_direct_tramp) + bti c + mov x10, x30 + mov x30, x9 + ret x10 +SYM_CODE_END(ftrace_stub_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ /* |