| Message ID | 20250401225842.429332654@goodmis.org (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | tracing: Clean up persistent ring buffer code | expand |
On Tue, Apr 01, 2025 at 06:58:13PM -0400, Steven Rostedt wrote: > From: Steven Rostedt <rostedt@goodmis.org> > > The reserve_mem kernel command line option may pass back a physical > address, but the memory is still part of the normal memory just like > using memblock_reserve() would be. This means that the physical memory ... using memblock_alloc() would be > returned by the reserve_mem command line option can be converted directly > to virtual memory by simply using phys_to_virt(). > > When freeing the buffer there's no need to call vunmap() anymore as the > memory allocated by reserve_mem is freed by the call to > reserve_mem_release_by_name(). > > Because the persistent ring buffer can also be allocated via the memmap > option, which *is* different than normal memory as it cannot be added back > to the buddy system, it must be treated differently. It still needs to be > virtually mapped to have access to it. It also can not be freed nor can it > ever be memory mapped to user space. > > Create a new trace_array flag called TRACE_ARRAY_FL_MEMMAP which gets set > if the buffer is created by the memmap option, and this will prevent the > buffer from being memory mapped by user space. > > Also increment the ref count for memmap'ed buffers so that they can never > be freed. > > Link: https://lore.kernel.org/all/Z-wFszhJ_9o4dc8O@kernel.org/ > > Suggested-by: Mike Rapoport <rppt@kernel.org> > Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> > --- > kernel/trace/trace.c | 23 ++++++++++++++++------- > kernel/trace/trace.h | 1 + > 2 files changed, 17 insertions(+), 7 deletions(-) > > diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c > index de9c237e5826..2f9c91f26d5b 100644 > --- a/kernel/trace/trace.c > +++ b/kernel/trace/trace.c > @@ -8505,6 +8505,10 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) > struct trace_iterator *iter = &info->iter; > int ret = 0; > > + /* A memmap'ed buffer is not supported for user space mmap */ > + if (iter->tr->flags & TRACE_ARRAY_FL_MEMMAP) > + return -ENODEV; > + > /* Currently the boot mapped buffer is not supported for mmap */ > if (iter->tr->flags & TRACE_ARRAY_FL_BOOT) > return -ENODEV; > @@ -9614,9 +9618,6 @@ static void free_trace_buffers(struct trace_array *tr) > #ifdef CONFIG_TRACER_MAX_TRACE > free_trace_buffer(&tr->max_buffer); > #endif > - > - if (tr->range_addr_start) > - vunmap((void *)tr->range_addr_start); > } > > static void init_trace_flags_index(struct trace_array *tr) > @@ -10710,6 +10711,7 @@ static inline void do_allocate_snapshot(const char *name) { } > __init static void enable_instances(void) > { > struct trace_array *tr; > + bool memmap_area = false; > char *curr_str; > char *name; > char *str; > @@ -10778,6 +10780,7 @@ __init static void enable_instances(void) > name); > continue; > } > + memmap_area = true; > } else if (tok) { > if (!reserve_mem_find_by_name(tok, &start, &size)) { > start = 0; > @@ -10800,7 +10803,10 @@ __init static void enable_instances(void) > continue; > } > > - addr = map_pages(start, size); > + if (memmap_area) > + addr = map_pages(start, size); > + else > + addr = (unsigned long)phys_to_virt(start); > if (addr) { > pr_info("Tracing: mapped boot instance %s at physical memory %pa of size 0x%lx\n", > name, &start, (unsigned long)size); > @@ -10827,10 +10833,13 @@ __init static void enable_instances(void) > update_printk_trace(tr); > > /* > - * If start is set, then this is a mapped buffer, and > - * cannot be deleted by user space, so keep the reference > - * to it. > + * memmap'd buffers can not be freed. > */ > + if (memmap_area) { > + tr->flags |= TRACE_ARRAY_FL_MEMMAP; > + tr->ref++; > + } > + > if (start) { > tr->flags |= TRACE_ARRAY_FL_BOOT | TRACE_ARRAY_FL_LAST_BOOT; > tr->range_name = no_free_ptr(rname); > diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h > index c20f6bcc200a..f9513dc14c37 100644 > --- a/kernel/trace/trace.h > +++ b/kernel/trace/trace.h > @@ -447,6 +447,7 @@ enum { > TRACE_ARRAY_FL_BOOT = BIT(1), > TRACE_ARRAY_FL_LAST_BOOT = BIT(2), > TRACE_ARRAY_FL_MOD_INIT = BIT(3), > + TRACE_ARRAY_FL_MEMMAP = BIT(4), > }; > > #ifdef CONFIG_MODULES > -- > 2.47.2 > >
On Wed, 2 Apr 2025 12:24:12 +0300 Mike Rapoport <rppt@kernel.org> wrote: > > The reserve_mem kernel command line option may pass back a physical > > address, but the memory is still part of the normal memory just like > > using memblock_reserve() would be. This means that the physical memory > > ... using memblock_alloc() would be Heh, I looked for examples of code that used free_reserved_area() and found initramfs.c which uses memblock_reserve(), which is why I picked that. I'll update. Thanks for reviewing Mike! -- Steve
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index de9c237e5826..2f9c91f26d5b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8505,6 +8505,10 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) struct trace_iterator *iter = &info->iter; int ret = 0; + /* A memmap'ed buffer is not supported for user space mmap */ + if (iter->tr->flags & TRACE_ARRAY_FL_MEMMAP) + return -ENODEV; + /* Currently the boot mapped buffer is not supported for mmap */ if (iter->tr->flags & TRACE_ARRAY_FL_BOOT) return -ENODEV; @@ -9614,9 +9618,6 @@ static void free_trace_buffers(struct trace_array *tr) #ifdef CONFIG_TRACER_MAX_TRACE free_trace_buffer(&tr->max_buffer); #endif - - if (tr->range_addr_start) - vunmap((void *)tr->range_addr_start); } static void init_trace_flags_index(struct trace_array *tr) @@ -10710,6 +10711,7 @@ static inline void do_allocate_snapshot(const char *name) { } __init static void enable_instances(void) { struct trace_array *tr; + bool memmap_area = false; char *curr_str; char *name; char *str; @@ -10778,6 +10780,7 @@ __init static void enable_instances(void) name); continue; } + memmap_area = true; } else if (tok) { if (!reserve_mem_find_by_name(tok, &start, &size)) { start = 0; @@ -10800,7 +10803,10 @@ __init static void enable_instances(void) continue; } - addr = map_pages(start, size); + if (memmap_area) + addr = map_pages(start, size); + else + addr = (unsigned long)phys_to_virt(start); if (addr) { pr_info("Tracing: mapped boot instance %s at physical memory %pa of size 0x%lx\n", name, &start, (unsigned long)size); @@ -10827,10 +10833,13 @@ __init static void enable_instances(void) update_printk_trace(tr); /* - * If start is set, then this is a mapped buffer, and - * cannot be deleted by user space, so keep the reference - * to it. + * memmap'd buffers can not be freed. */ + if (memmap_area) { + tr->flags |= TRACE_ARRAY_FL_MEMMAP; + tr->ref++; + } + if (start) { tr->flags |= TRACE_ARRAY_FL_BOOT | TRACE_ARRAY_FL_LAST_BOOT; tr->range_name = no_free_ptr(rname); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c20f6bcc200a..f9513dc14c37 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -447,6 +447,7 @@ enum { TRACE_ARRAY_FL_BOOT = BIT(1), TRACE_ARRAY_FL_LAST_BOOT = BIT(2), TRACE_ARRAY_FL_MOD_INIT = BIT(3), + TRACE_ARRAY_FL_MEMMAP = BIT(4), }; #ifdef CONFIG_MODULES