> +static inline void pks_update_protection(int pkey, unsigned long protection)
> +{
> + current->thread.saved_pkrs = update_pkey_val(current->thread.saved_pkrs,
> + pkey, protection);
> + preempt_disable();
> + write_pkrs(current->thread.saved_pkrs);
> + preempt_enable();
> +}
Why does this need preempt count manipulation in addition to the
get/put_cpu_var() inside of write_pkrs()?
> +/**
> + * PKS access control functions
> + *
> + * Change the access of the domain specified by the pkey. These are global
> + * updates. They only affects the current running thread. It is undefined and
> + * a bug for users to call this without having allocated a pkey and using it as
> + * pkey here.
> + *
> + * pks_mknoaccess()
> + * Disable all access to the domain
> + * pks_mkread()
> + * Make the domain Read only
> + * pks_mkrdwr()
> + * Make the domain Read/Write
> + *
> + * @pkey the pkey for which the access should change.
> + *
> + */
> +void pks_mknoaccess(int pkey)
> +{
> + pks_update_protection(pkey, PKEY_DISABLE_ACCESS);
> +}
> +EXPORT_SYMBOL_GPL(pks_mknoaccess);
These are named like PTE manipulation functions, which is kinda weird.
What's wrong with: pks_disable_access(pkey) ?
> +void pks_mkread(int pkey)
> +{
> + pks_update_protection(pkey, PKEY_DISABLE_WRITE);
> +}
> +EXPORT_SYMBOL_GPL(pks_mkread);
I really don't like this name. It doesn't make readable, or even
read-only, *especially* if it was already access-disabled.
> +static const char pks_key_user0[] = "kernel";
> +
> +/* Store names of allocated keys for debug. Key 0 is reserved for the kernel. */
> +static const char *pks_key_users[PKS_NUM_KEYS] = {
> + pks_key_user0
> +};
> +
> +/*
> + * Each key is represented by a bit. Bit 0 is set for key 0 and reserved for
> + * its use. We use ulong for the bit operations but only 16 bits are used.
> + */
> +static unsigned long pks_key_allocation_map = 1 << PKS_KERN_DEFAULT_KEY;
> +
> +/*
> + * pks_key_alloc - Allocate a PKS key
> + *
> + * @pkey_user: String stored for debugging of key exhaustion. The caller is
> + * responsible to maintain this memory until pks_key_free().
> + */
> +int pks_key_alloc(const char * const pkey_user)
> +{
> + int nr;
> +
> + if (!cpu_feature_enabled(X86_FEATURE_PKS))
> + return -EINVAL;
I'm not sure I like -EINVAL for this. I thought we returned -ENOSPC for
this case for user pkeys.
> + while (1) {
> + nr = find_first_zero_bit(&pks_key_allocation_map, PKS_NUM_KEYS);
> + if (nr >= PKS_NUM_KEYS) {
> + pr_info("Cannot allocate supervisor key for %s.\n",
> + pkey_user);
> + return -ENOSPC;
> + }
> + if (!test_and_set_bit_lock(nr, &pks_key_allocation_map))
> + break;
> + }
> +
> + /* for debugging key exhaustion */
> + pks_key_users[nr] = pkey_user;
> +
> + return nr;
> +}
> +EXPORT_SYMBOL_GPL(pks_key_alloc);
> +
> +/*
> + * pks_key_free - Free a previously allocate PKS key
> + *
> + * @pkey: Key to be free'ed
> + */
> +void pks_key_free(int pkey)
> +{
> + if (!cpu_feature_enabled(X86_FEATURE_PKS))
> + return;
> +
> + if (pkey >= PKS_NUM_KEYS || pkey <= PKS_KERN_DEFAULT_KEY)
> + return;
This seems worthy of a WARN_ON_ONCE() at least. It's essentially
corrupt data coming into a kernel API.
