On Mon, Apr 01, 2019 at 10:58:19AM +0200, Daniel Bristot de Oliveira wrote:
> diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
> index 8aa65fbbd764..ab75b222a7e2 100644
> --- a/arch/x86/kernel/jump_label.c
> +++ b/arch/x86/kernel/jump_label.c
> @@ -15,6 +15,7 @@
> #include <asm/kprobes.h>
> #include <asm/alternative.h>
> #include <asm/text-patching.h>
> +#include <linux/slab.h>
>
> union jump_code_union {
> char code[JUMP_LABEL_NOP_SIZE];
> @@ -111,6 +112,93 @@ void arch_jump_label_transform(struct jump_entry *entry,
> mutex_unlock(&text_mutex);
> }
>
> +unsigned int entry_vector_max_elem __read_mostly;
> +struct text_patch_loc *entry_vector;
> +unsigned int entry_vector_nr_elem;
> +
> +void arch_jump_label_init(void)
> +{
> + entry_vector = (void *) __get_free_page(GFP_KERNEL);
> +
> + if (WARN_ON_ONCE(!entry_vector))
> + return;
> +
> + entry_vector_max_elem = PAGE_SIZE / sizeof(struct text_patch_loc);
> + return;
> +}
> +
> +int arch_jump_label_transform_queue(struct jump_entry *entry,
> + enum jump_label_type type)
> +{
> + struct text_patch_loc *tp;
> + void *entry_code;
> +
> + /*
> + * Batch mode disabled before being able to allocate memory:
> + * Fallback to the non-batching mode.
> + */
> + if (unlikely(!entry_vector_max_elem)) {
> + if (!slab_is_available() || early_boot_irqs_disabled)
See, the thing is, you never use slab, so that slab check is completely
wrong.
> + goto fallback;
> +
> + arch_jump_label_init();
> + }
> +
> + /*
> + * No more space in the vector, tell upper layer to apply
> + * the queue before continuing.
> + */
> + if (entry_vector_nr_elem == entry_vector_max_elem)
> + return -ENOSPC;
> +
> + tp = &entry_vector[entry_vector_nr_elem];
> +
> + entry_code = (void *)jump_entry_code(entry);
> +
> + /*
> + * The int3 handler will do a bsearch in the queue, so we need entries
> + * to be sorted. We can survive an unsorted list by rejecting the entry,
> + * forcing the generic jump_label code to apply the queue. Warning once,
> + * to raise the attention to the case of an unsorted entry that is
> + * better not happen, because, in the worst case we will perform in the
> + * same way as we do without batching - with some more overhead.
> + */
> + if (entry_vector_nr_elem > 0) {
> + int prev_idx = entry_vector_nr_elem - 1;
> + struct text_patch_loc *prev_tp = &entry_vector[prev_idx];
> +
> + if (WARN_ON_ONCE(prev_tp->addr > entry_code))
> + return -EINVAL;
> + }
> +
> + __jump_label_set_jump_code(entry, type,
> + (union jump_code_union *) &tp->opcode, 0);
> +
> + tp->addr = entry_code;
> + tp->detour = entry_code + JUMP_LABEL_NOP_SIZE;
> + tp->len = JUMP_LABEL_NOP_SIZE;
> +
> + entry_vector_nr_elem++;
> +
> + return 0;
> +
> +fallback:
> + arch_jump_label_transform(entry, type);
> + return 0;
> +}
So how about we do something like:
+static struct bp_patching_desc {
+ int nr_entries;
+ struct text_patch_loc vec[PAGE_SIZE / sizeof(struct text_patch_loc)];
+} bp_patching;
and call it a day?
Then we have static storage, no allocation, no fail paths.
Also note that I removed that whole in_progress thing, as that is
completely redudant vs !!nr_entries.
