[PATCH V2 2/5] ocxl: Initiate a TLB invalidate command

Frederic Barrat fbarrat at linux.ibm.com
Mon Nov 23 21:37:35 AEDT 2020



On 20/11/2020 18:32, Christophe Lombard wrote:
> When a TLB Invalidate is required for the Logical Partition, the following
> sequence has to be performed:
> 
> 1. Load MMIO ATSD AVA register with the necessary value, if required.
> 2. Write the MMIO ATSD launch register to initiate the TLB Invalidate
>     command.
> 3. Poll the MMIO ATSD status register to determine when the TLB Invalidate
>     has been completed.
> 
> Signed-off-by: Christophe Lombard <clombard at linux.vnet.ibm.com>
> ---
>   arch/powerpc/include/asm/pnv-ocxl.h   | 50 ++++++++++++++++++++++++
>   arch/powerpc/platforms/powernv/ocxl.c | 55 +++++++++++++++++++++++++++
>   2 files changed, 105 insertions(+)
> 
> diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h
> index 3f38aed7100c..9c90e87e7659 100644
> --- a/arch/powerpc/include/asm/pnv-ocxl.h
> +++ b/arch/powerpc/include/asm/pnv-ocxl.h
> @@ -3,12 +3,59 @@
>   #ifndef _ASM_PNV_OCXL_H
>   #define _ASM_PNV_OCXL_H
> 
> +#include <linux/bitfield.h>
>   #include <linux/pci.h>
> 
>   #define PNV_OCXL_TL_MAX_TEMPLATE        63
>   #define PNV_OCXL_TL_BITS_PER_RATE       4
>   #define PNV_OCXL_TL_RATE_BUF_SIZE       ((PNV_OCXL_TL_MAX_TEMPLATE+1) * PNV_OCXL_TL_BITS_PER_RATE / 8)
> 
> +#define PNV_OCXL_ATSD_TIMEOUT		1
> +
> +/* TLB Management Instructions */
> +#define PNV_OCXL_ATSD_LNCH		0x00
> +/* Radix Invalidate */
> +#define   PNV_OCXL_ATSD_LNCH_R		PPC_BIT(0)
> +/* Radix Invalidation Control
> + * 0b00 Just invalidate TLB.
> + * 0b01 Invalidate just Page Walk Cache.
> + * 0b10 Invalidate TLB, Page Walk Cache, and any
> + * caching of Partition and Process Table Entries.
> + */
> +#define   PNV_OCXL_ATSD_LNCH_RIC	PPC_BITMASK(1, 2)
> +/* Number and Page Size of translations to be invalidated */
> +#define   PNV_OCXL_ATSD_LNCH_LP		PPC_BITMASK(3, 10)
> +/* Invalidation Criteria
> + * 0b00 Invalidate just the target VA.
> + * 0b01 Invalidate matching PID.
> + */
> +#define   PNV_OCXL_ATSD_LNCH_IS		PPC_BITMASK(11, 12)
> +/* 0b1: Process Scope, 0b0: Partition Scope */
> +#define   PNV_OCXL_ATSD_LNCH_PRS	PPC_BIT(13)
> +/* Invalidation Flag */
> +#define   PNV_OCXL_ATSD_LNCH_B		PPC_BIT(14)
> +/* Actual Page Size to be invalidated
> + * 000 4KB
> + * 101 64KB
> + * 001 2MB
> + * 010 1GB
> + */
> +#define   PNV_OCXL_ATSD_LNCH_AP		PPC_BITMASK(15, 17)
> +/* Defines the large page select
> + * L=0b0 for 4KB pages
> + * L=0b1 for large pages)
> + */
> +#define   PNV_OCXL_ATSD_LNCH_L		PPC_BIT(18)
> +/* Process ID */
> +#define   PNV_OCXL_ATSD_LNCH_PID	PPC_BITMASK(19, 38)
> +/* NoFlush – Assumed to be 0b0 */
> +#define   PNV_OCXL_ATSD_LNCH_F		PPC_BIT(39)
> +#define   PNV_OCXL_ATSD_LNCH_OCAPI_SLBI	PPC_BIT(40)
> +#define   PNV_OCXL_ATSD_LNCH_OCAPI_SINGLETON	PPC_BIT(41)
> +#define PNV_OCXL_ATSD_AVA		0x08
> +#define   PNV_OCXL_ATSD_AVA_AVA		PPC_BITMASK(0, 51)
> +#define PNV_OCXL_ATSD_STAT		0x10
> +
>   int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled, u16 *supported);
>   int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count);
> 
> @@ -31,4 +78,7 @@ int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle);
>   int pnv_ocxl_map_lpar(struct pci_dev *dev, uint64_t lparid,
>   		      uint64_t lpcr, void __iomem **arva);
>   void pnv_ocxl_unmap_lpar(void __iomem **arva);
> +void pnv_ocxl_tlb_invalidate(void __iomem **arva,
> +			     unsigned long pid,
> +			     unsigned long addr);
>   #endif /* _ASM_PNV_OCXL_H */
> diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c
> index bc20cf867900..07878496954b 100644
> --- a/arch/powerpc/platforms/powernv/ocxl.c
> +++ b/arch/powerpc/platforms/powernv/ocxl.c
> @@ -531,3 +531,58 @@ void pnv_ocxl_unmap_lpar(void __iomem **arva)
>   	iounmap(*arva);
>   }
>   EXPORT_SYMBOL_GPL(pnv_ocxl_unmap_lpar);
> +
> +void pnv_ocxl_tlb_invalidate(void __iomem **arva,


Similarly to the previous patch, there's no reason why arva should be a 
double-pointer.


> +			     unsigned long pid,
> +			     unsigned long addr)
> +{
> +	unsigned long timeout = jiffies + (HZ * PNV_OCXL_ATSD_TIMEOUT);
> +	uint64_t val = 0ull;
> +	int pend;
> +
> +	if (!(*arva))
> +		return;
> +
> +	if (addr) {
> +		/* load Abbreviated Virtual Address register with
> +		 * the necessary value
> +		 */
> +		val |= FIELD_PREP(PNV_OCXL_ATSD_AVA_AVA, addr >> (63-51));
> +		out_be64(*arva + PNV_OCXL_ATSD_AVA, val);
> +	}
> +
> +	/* Write access initiates a shoot down to initiate the
> +	 * TLB Invalidate command
> +	 */
> +	val = PNV_OCXL_ATSD_LNCH_R;
> +	if (addr) {
> +		val |= FIELD_PREP(PNV_OCXL_ATSD_LNCH_RIC, 0b00);
> +		val |= FIELD_PREP(PNV_OCXL_ATSD_LNCH_IS, 0b00);
> +	} else {
> +		val |= FIELD_PREP(PNV_OCXL_ATSD_LNCH_RIC, 0b10);
> +		val |= FIELD_PREP(PNV_OCXL_ATSD_LNCH_IS, 0b01);
> +		val |= PNV_OCXL_ATSD_LNCH_OCAPI_SINGLETON;
> +	}
> +	val |= PNV_OCXL_ATSD_LNCH_PRS;
> +	val |= FIELD_PREP(PNV_OCXL_ATSD_LNCH_AP, 0b101);



So we hard code a page size of 64k. The mmu notifier loops over 
PAGE_SIZE. It would be cleaner to pass the page size as an argument and 
code AP based on it.

   Fred


> +	val |= FIELD_PREP(PNV_OCXL_ATSD_LNCH_PID, pid);
> +	out_be64(*arva + PNV_OCXL_ATSD_LNCH, val);
> +
> +	/* Poll the ATSD status register to determine when the
> +	 * TLB Invalidate has been completed.
> +	 */
> +	val = in_be64(*arva + PNV_OCXL_ATSD_STAT);
> +	pend = val >> 63;
> +
> +	while (pend) {
> +		if (time_after_eq(jiffies, timeout)) {
> +			pr_err("%s - Timeout while reading XTS MMIO ATSD status register (val=%#llx, pidr=0x%lx)\n",
> +			       __func__, val, pid);
> +			return;
> +		}
> +		cpu_relax();
> +		val = in_be64(*arva + PNV_OCXL_ATSD_STAT);
> +		pend = val >> 63;
> +	}
> +}
> +EXPORT_SYMBOL_GPL(pnv_ocxl_tlb_invalidate);
> 


More information about the Linuxppc-dev mailing list