Re: [PATCH 04/32] x86/intel_rdt: Add L3 cache capacity bitmask management

[Marcelo Tosatti <mtosatti@redhat.com>]

On Tue, Jul 12, 2016 at 06:02:37PM -0700, Fenghua Yu wrote:
> From: Vikas Shivappa <vikas.shivappa@linux.intel.com>
> 
> This patch adds different APIs to manage the L3 cache capacity bitmask.
> The capacity bit mask(CBM) needs to have only contiguous bits set. The
> current implementation has a global CBM for each class of service id.
> There are APIs added to update the CBM via MSR write to IA32_L3_MASK_n
> on all packages. Other APIs are to read and write entries to the
> clos_cbm_table.
> 
> Signed-off-by: Vikas Shivappa <vikas.shivappa@linux.intel.com>
> Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
> Reviewed-by: Tony Luck <tony.luck@intel.com>
> ---
>  arch/x86/include/asm/intel_rdt.h |   4 ++
>  arch/x86/kernel/cpu/intel_rdt.c  | 133 ++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 136 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
> index 88b7643..4f45dc8 100644
> --- a/arch/x86/include/asm/intel_rdt.h
> +++ b/arch/x86/include/asm/intel_rdt.h
> @@ -3,6 +3,10 @@
>  
>  #ifdef CONFIG_INTEL_RDT
>  
> +#define MAX_CBM_LENGTH			32
> +#define IA32_L3_CBM_BASE		0xc90
> +#define CBM_FROM_INDEX(x)		(IA32_L3_CBM_BASE + x)
> +
>  struct clos_cbm_table {
>  	unsigned long l3_cbm;
>  	unsigned int clos_refcnt;
> diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
> index d79213a..6ad5b48 100644
> --- a/arch/x86/kernel/cpu/intel_rdt.c
> +++ b/arch/x86/kernel/cpu/intel_rdt.c
> @@ -34,8 +34,22 @@ static struct clos_cbm_table *cctable;
>   * closid availability bit map.
>   */
>  unsigned long *closmap;
> +/*
> + * Mask of CPUs for writing CBM values. We only need one CPU per-socket.
> + */
> +static cpumask_t rdt_cpumask;
> +/*
> + * Temporary cpumask used during hot cpu notificaiton handling. The usage
> + * is serialized by hot cpu locks.
> + */
> +static cpumask_t tmp_cpumask;
>  static DEFINE_MUTEX(rdt_group_mutex);
>  
> +struct rdt_remote_data {
> +	int msr;
> +	u64 val;
> +};
> +
>  static inline void closid_get(u32 closid)
>  {
>  	struct clos_cbm_table *cct = &cctable[closid];
> @@ -82,11 +96,126 @@ static void closid_put(u32 closid)
>  		closid_free(closid);
>  }
>  
> +static bool cbm_validate(unsigned long var)
> +{
> +	u32 max_cbm_len = boot_cpu_data.x86_cache_max_cbm_len;
> +	unsigned long first_bit, zero_bit;
> +	u64 max_cbm;
> +
> +	if (bitmap_weight(&var, max_cbm_len) < 1)
> +		return false;
> +
> +	max_cbm = (1ULL << max_cbm_len) - 1;
> +	if (var & ~max_cbm)
> +		return false;
> +
> +	first_bit = find_first_bit(&var, max_cbm_len);
> +	zero_bit = find_next_zero_bit(&var, max_cbm_len, first_bit);
> +
> +	if (find_next_bit(&var, max_cbm_len, zero_bit) < max_cbm_len)
> +		return false;
> +
> +	return true;
> +}
> +
> +static int clos_cbm_table_read(u32 closid, unsigned long *l3_cbm)
> +{
> +	u32 maxid = boot_cpu_data.x86_cache_max_closid;
> +
> +	lockdep_assert_held(&rdt_group_mutex);
> +
> +	if (closid >= maxid)
> +		return -EINVAL;
> +
> +	*l3_cbm = cctable[closid].l3_cbm;
> +
> +	return 0;
> +}
> +
> +/*
> + * clos_cbm_table_update() - Update a clos cbm table entry.
> + * @closid: the closid whose cbm needs to be updated
> + * @cbm: the new cbm value that has to be updated
> + *
> + * This assumes the cbm is validated as per the interface requirements
> + * and the cache allocation requirements(through the cbm_validate).
> + */
> +static int clos_cbm_table_update(u32 closid, unsigned long cbm)
> +{
> +	u32 maxid = boot_cpu_data.x86_cache_max_closid;
> +
> +	lockdep_assert_held(&rdt_group_mutex);
> +
> +	if (closid >= maxid)
> +		return -EINVAL;
> +
> +	cctable[closid].l3_cbm = cbm;
> +
> +	return 0;
> +}
> +
> +static bool cbm_search(unsigned long cbm, u32 *closid)
> +{
> +	u32 maxid = boot_cpu_data.x86_cache_max_closid;
> +	u32 i;
> +
> +	for (i = 0; i < maxid; i++) {
> +		if (cctable[i].clos_refcnt &&
> +		    bitmap_equal(&cbm, &cctable[i].l3_cbm, MAX_CBM_LENGTH)) {
> +			*closid = i;
> +			return true;
> +		}
> +	}
> +
> +	return false;
> +}
> +
> +static void closcbm_map_dump(void)
> +{
> +	u32 i;
> +
> +	pr_debug("CBMMAP\n");
> +	for (i = 0; i < boot_cpu_data.x86_cache_max_closid; i++) {
> +		pr_debug("l3_cbm: 0x%x,clos_refcnt: %u\n",
> +		 (unsigned int)cctable[i].l3_cbm, cctable[i].clos_refcnt);
> +	}
> +}
> +
> +static void msr_cpu_update(void *arg)
> +{
> +	struct rdt_remote_data *info = arg;
> +
> +	wrmsrl(info->msr, info->val);
> +}
> +
> +/*
> + * msr_update_all() - Update the msr for all packages.
> + */
> +static inline void msr_update_all(int msr, u64 val)
> +{
> +	struct rdt_remote_data info;
> +
> +	info.msr = msr;
> +	info.val = val;
> +	on_each_cpu_mask(&rdt_cpumask, msr_cpu_update, &info, 1);
> +}

How does this patchset handle the following condition:

6) Create reservations in such a way that the sum is larger than
total amount of cache, and CPU pinning (example from Karen Noel):

VM-1 on socket-1 with 80% of reservation.
VM-2 on socket-2 with 80% of reservation.
VM-1 pinned to socket-1.
VM-2 pinned to socket-2.


> +
> +static inline bool rdt_cpumask_update(int cpu)
> +{
> +	cpumask_and(&tmp_cpumask, &rdt_cpumask, topology_core_cpumask(cpu));
> +	if (cpumask_empty(&tmp_cpumask)) {
> +		cpumask_set_cpu(cpu, &rdt_cpumask);
> +		return true;
> +	}
> +
> +	return false;
> +}
> +
>  static int __init intel_rdt_late_init(void)
>  {
>  	struct cpuinfo_x86 *c = &boot_cpu_data;
>  	u32 maxid, max_cbm_len;
> -	int err = 0, size;
> +	int err = 0, size, i;
>  
>  	if (!cpu_has(c, X86_FEATURE_CAT_L3))
>  		return -ENODEV;
> @@ -109,6 +238,8 @@ static int __init intel_rdt_late_init(void)
>  		goto out_err;
>  	}
>  
> +	for_each_online_cpu(i)
> +		rdt_cpumask_update(i);
>  	pr_info("Intel cache allocation enabled\n");
>  out_err:
>  
> -- 
> 2.5.0