ocxl: Mmio invalidation support
Subsystems (4)
v3 cover ocxl: Mmio invalidation support
OpenCAPI 4.0/5.0 with TLBI/SLBI Snooping, is not used due to performance problems caused by the PAU having to process all incoming TLBI/SLBI commands which will cause them to back up on the PowerBus.
When the Address Translation Mode requires TLB operations to be initiated using MMIO registers, a set of registers like the following is used:
• XTS MMIO ATSD0 LPARID register
• XTS MMIO ATSD0 AVA register
• XTS MMIO ATSD0 launch register, write access initiates a shoot down
• XTS MMIO ATSD0 status register
The MMIO based mechanism also blocks the NPU/PAU from snooping TLBIE commands from the PowerBus.
The Shootdown commands (ATSD) will be generated using MMIO registers in the NPU/PAU and sent to the device.
---
Changelog[v3]
- Rebase to latest upstream.
- Add page_size argument in pnv_ocxl_tlb_invalidate()
- Remove double pointer
Changelog[v2]
- Rebase to latest upstream.
- Create a set of smaller patches
- Move the device tree parsing and ioremap() for the shootdown page in a platform-specific file (powernv)
- Release the shootdown page in release_xsl()
- Initialize atsd_lock
- Move the code to initiate the TLB Invalidate command in a platform-specific file (powernv)
- Use the notifier invalidate_range
---
Christophe Lombard (5):
ocxl: Assign a register set to a Logical Partition
ocxl: Initiate a TLB invalidate command
ocxl: Update the Process Element Entry
ocxl: Add mmu notifier
ocxl: Add new kernel traces
arch/powerpc/include/asm/pnv-ocxl.h | 54 ++++++++++++ arch/powerpc/platforms/powernv/ocxl.c | 115 ++++++++++++++++++++++++++ drivers/misc/ocxl/context.c | 4 +- drivers/misc/ocxl/link.c | 70 +++++++++++++++- drivers/misc/ocxl/ocxl_internal.h | 9 +- drivers/misc/ocxl/trace.h | 64 ++++++++++++++ drivers/scsi/cxlflash/ocxl_hw.c | 6 +- include/misc/ocxl.h | 2 +- 8 files changed, 315 insertions(+), 9 deletions(-)
Signature · 1 line
2.28.0
PATCH v3 1/5 ocxl: Assign a register set to a Logical Partition
Platform specific function to assign a register set to a Logical Partition. The "ibm,mmio-atsd" property, provided by the firmware, contains the 16 base ATSD physical addresses (ATSD0 through ATSD15) of the set of MMIO registers (XTS MMIO ATSDx LPARID/AVA/launch/status register).
For the time being, the ATSD0 set of registers is used by default.
--- arch/powerpc/include/asm/pnv-ocxl.h | 3 ++ arch/powerpc/platforms/powernv/ocxl.c | 45 +++++++++++++++++++++++++++ 2 files changed, 48 insertions(+)
arch/powerpc/include/asm/pnv-ocxl.h +3 -0
@@ -28,4 +28,7 @@ int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, void **pvoid pnv_ocxl_spa_release (void *platform_data);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);#endif /* _ASM_PNV_OCXL_H */
arch/powerpc/platforms/powernv/ocxl.c +45 -0
48 lines not on this page · raw message
Signature · 1 line
2.28.0
Re: [PATCH V3 1/5] ocxl: Assign a register set to a Logical Partition
Quoted 9 lines · Christophe Lombard
Platform specific function to assign a register set to a Logical Partition. The "ibm,mmio-atsd" property, provided by the firmware, contains the 16 base ATSD physical addresses (ATSD0 through ATSD15) of the set of MMIO registers (XTS MMIO ATSDx LPARID/AVA/launch/status register).
For the time being, the ATSD0 set of registers is used by default.
Signed-off-by Christophe Lombard <[email protected]>---
Looks good, thanks for the updates!
Quoted 70 lines
arch/powerpc/include/asm/pnv-ocxl.h | 3 ++ arch/powerpc/platforms/powernv/ocxl.c | 45 +++++++++++++++++++++++++++ 2 files changed, 48 insertions(+)arch/powerpc/include/asm/pnv-ocxl.h +3
-0@@ -28,4 +28,7 @@ int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, void **pvoid pnv_ocxl_spa_release (void *platform_data);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);#endif /* _ASM_PNV_OCXL_H */ arch/powerpc/platforms/powernv/ocxl.c +45
-0@@ -483,3 +483,48 @@ int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle)return rc; }EXPORT_SYMBOL_GPL (pnv_ocxl_spa_remove_pe_from_cache); + +int pnv_ocxl_map_lpar (struct pci_dev *dev,uint64_t lparid, +uint64_t lpcr,void __iomem **arva) +{ +struct pci_controller *hose =pci_bus_to_host (dev->bus); +struct pnv_phb *phb = hose->private_data; +u64 mmio_atsd; +int rc; + +/* ATSD physical address. +* ATSD LAUNCH register: write access initiates a shoot down to +* initiate the TLB Invalidate command. +*/ + rc =of_property_read_u64_index (hose->dn,"ibm,mmio-atsd" , +0 , &mmio_atsd); +if (rc) { +dev_info (&dev->dev,"No available ATSD found\n" ); +return rc; + } + +/* Assign a register set to a Logical Partition and MMIO ATSD +* LPARID register to the required value. +*/ + rc =opal_npu_map_lpar (phb->opal_id,pci_dev_id (dev), + lparid, lpcr); +if (rc) { +dev_err (&dev->dev,"Error mapping device to LPAR: %d\n" , rc); +return rc; + } + + *arva =ioremap (mmio_atsd,24 ); +if (!(*arva)) { +dev_warn (&dev->dev,"ioremap failed - mmio_atsd: %#llx\n" , mmio_atsd); + rc = -ENOMEM ; + } + +return rc; +} +EXPORT_SYMBOL_GPL (pnv_ocxl_map_lpar); + +void pnv_ocxl_unmap_lpar (void __iomem *arva) +{ +iounmap (arva); +} +EXPORT_SYMBOL_GPL (pnv_ocxl_unmap_lpar);
PATCH v3 2/5 ocxl: Initiate a TLB invalidate command
In reply to Christophe LombardWhen 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.
--- arch/powerpc/include/asm/pnv-ocxl.h | 51 +++++++++++++++++++ arch/powerpc/platforms/powernv/ocxl.c | 70 +++++++++++++++++++++++++++ 2 files changed, 121 insertions(+)
arch/powerpc/include/asm/pnv-ocxl.h +51 -0
@@ -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 +78,8 @@ 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, +unsigned long page_size);#endif /* _ASM_PNV_OCXL_H */
arch/powerpc/platforms/powernv/ocxl.c +70 -0
73 lines not on this page · raw message
Signature · 1 line
2.28.0
Re: [PATCH V3 2/5] ocxl: Initiate a TLB invalidate command
Quoted 130 lines · Christophe Lombard
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 <[email protected]>--- arch/powerpc/include/asm/pnv-ocxl.h | 51 +++++++++++++++++++ arch/powerpc/platforms/powernv/ocxl.c | 70 +++++++++++++++++++++++++++ 2 files changed, 121 insertions(+)arch/powerpc/include/asm/pnv-ocxl.h +51
-0@@ -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 +78,8 @@ 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, +unsigned long page_size);#endif /* _ASM_PNV_OCXL_H */ arch/powerpc/platforms/powernv/ocxl.c +34
-0@@ -528,3 +528,73 @@ 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, +unsigned long pid, +unsigned long addr, +unsigned long page_size) +{ +unsigned long timeout = jiffies + (HZ *PNV_OCXL_ATSD_TIMEOUT ); +u64 val =0ull ; +int pend; +u8 size; + +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 ; + }
arch/powerpc/platforms/powernv/ocxl.c void pnv_ocxl_unmap_lpar(void __iomem *arva) · line 574
Quoted 10 lines
arch/powerpc/platforms/powernv/ocxl.c +10
-0+ val |=PNV_OCXL_ATSD_LNCH_PRS ; +/* Actual Page Size to be invalidated +* 000 4KB +* 101 64KB +* 001 2MB +* 010 1GB +*/ + size =0b101 ; +if (page_size ==0x10000 ) + size =0b000 ;
Ooops, typo, we want page_size == 0x1000
Fred
Quoted 27 lines
arch/powerpc/platforms/powernv/ocxl.c +26
-0+if (page_size ==0x200000 ) + size =0b001 ; +if (page_size ==0x40000000 ) + size =0b010 ; + val |=FIELD_PREP (PNV_OCXL_ATSD_LNCH_AP , size); + 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);
PATCH v3 3/5 ocxl: Update the Process Element Entry
In reply to Christophe LombardTo complete the MMIO based mechanism, the fields: PASID, bus, device and function of the Process Element Entry have to be filled. (See OpenCAPI Power Platform Architecture document)
Hypervisor Process Element Entry
Word
0 1 .... 7 8 ...... 12 13 ..15 16.... 19 20 ........... 31 0 OSL Configuration State (0:31) 1 OSL Configuration State (32:63)
2 PASID | Reserved
3 Bus | Device |Function | Reserved
4 Reserved
5 Reserved
6 ....
--- drivers/misc/ocxl/context.c | 4 +++- drivers/misc/ocxl/link.c | 4 +++- drivers/misc/ocxl/ocxl_internal.h | 9 ++++++--- drivers/scsi/cxlflash/ocxl_hw.c | 6 ++++-- include/misc/ocxl.h | 2 +- 5 files changed, 17 insertions(+), 8 deletions(-)
drivers/misc/ocxl/context.c +3 -1
@@ -70,6 +70,7 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm) {int rc;unsigned long pidr =0 ; +struct pci_dev *dev;// Locks both status & tidr mutex_lock (&ctx->status_mutex);
@@ -81,8 +82,9 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)if (mm) pidr = mm->context.id; + dev =to_pci_dev (ctx->afu->fn->dev.parent); rc =ocxl_link_add_pe (ctx->afu->fn->link, ctx->pasid, pidr, ctx->tidr, - amr, mm, xsl_fault_error, ctx); + amr,pci_dev_id (dev), mm, xsl_fault_error, ctx);if (rc) goto out;
drivers/misc/ocxl/link.c +3 -1
@@ -494,7 +494,7 @@ static u64 calculate_cfg_state(bool kernel) }int ocxl_link_add_pe (void *link_handle,int pasid,u32 pidr,u32 tidr, -u64 amr,struct mm_struct *mm, +u64 amr,u16 bdf,struct mm_struct *mm,void (*xsl_err_cb)(void *data,u64 addr,u64 dsisr),void *xsl_err_data) {
@@ -529,6 +529,8 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,memset (pe,0 ,sizeof (struct ocxl_process_element )); pe->config_state =cpu_to_be64 (calculate_cfg_state (pidr ==0 )); + pe->pasid =cpu_to_be32 (pasid << (31 -19 )); + pe->bdf =cpu_to_be16 (bdf); pe->lpid =cpu_to_be32 (mfspr (SPRN_LPID )); pe->pid =cpu_to_be32 (pidr); pe->tid =cpu_to_be32 (tidr);
drivers/misc/ocxl/ocxl_internal.h +6 -3
@@ -84,13 +84,16 @@ struct ocxl_context {struct ocxl_process_element {__be64 config_state; -__be32 reserved1[11 ]; +__be32 pasid; +__be16 bdf; +__be16 reserved1; +__be32 reserved2[9 ];__be32 lpid;__be32 tid;__be32 pid; -__be32 reserved2[10 ]; +__be32 reserved3[10 ];__be64 amr; -__be32 reserved3[3 ]; +__be32 reserved4[3 ];__be32 software_state; };
drivers/scsi/cxlflash/ocxl_hw.c +4 -2
@@ -329,6 +329,7 @@ static int start_context(struct ocxlflash_context *ctx)struct ocxl_hw_afu *afu = ctx->hw_afu;struct ocxl_afu_config *acfg = &afu->acfg;void *link_token = afu->link_token; +struct pci_dev *pdev = afu->pdev;struct device *dev = afu->dev;bool master = ctx->master;struct mm_struct *mm;
@@ -360,8 +361,9 @@ static int start_context(struct ocxlflash_context *ctx) mm = current->mm; } - rc =ocxl_link_add_pe (link_token, ctx->pe, pid,0 ,0 , mm, - ocxlflash_xsl_fault, ctx); + rc =ocxl_link_add_pe (link_token, ctx->pe, pid,0 ,0 , +pci_dev_id (pdev), mm, ocxlflash_xsl_fault, + ctx);if (unlikely (rc)) {dev_err (dev,"%s: ocxl_link_add_pe failed rc=%d\n" , __func__, rc);
include/misc/ocxl.h +1 -1
@@ -447,7 +447,7 @@ void ocxl_link_release(struct pci_dev *dev, void *link_handle);* defined */ int ocxl_link_add_pe (void *link_handle,int pasid,u32 pidr,u32 tidr, -u64 amr,struct mm_struct *mm, +u64 amr,u16 bdf,struct mm_struct *mm,void (*xsl_err_cb)(void *data,u64 addr,u64 dsisr),void *xsl_err_data);
Signature · 1 line
2.28.0
Re: [PATCH V3 3/5] ocxl: Update the Process Element Entry
Quoted 15 lines · Christophe Lombard
To complete the MMIO based mechanism, the fields: PASID, bus, device and function of the Process Element Entry have to be filled. (See OpenCAPI Power Platform Architecture document)
Hypervisor Process Element Entry
Word0 1 .... 7 8 ...... 12 13 ..15 16.... 19 20 ........... 310 OSL Configuration State (0:31)
1 OSL Configuration State (32:63)
2 PASID | Reserved
3 Bus | Device |Function | Reserved
4 Reserved
5 Reserved
6 ....
Quoted 2 lines
Signed-off-by Christophe Lombard <[email protected]>---
LGTM
Quoted 113 lines
drivers/misc/ocxl/context.c | 4 +++- drivers/misc/ocxl/link.c | 4 +++- drivers/misc/ocxl/ocxl_internal.h | 9 ++++++--- drivers/scsi/cxlflash/ocxl_hw.c | 6 ++++-- include/misc/ocxl.h | 2 +- 5 files changed, 17 insertions(+), 8 deletions(-)drivers/misc/ocxl/context.c +3
-1@@ -70,6 +70,7 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm) {int rc;unsigned long pidr =0 ; +struct pci_dev *dev;// Locks both status & tidr mutex_lock (&ctx->status_mutex);@@ -81,8 +82,9 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)if (mm) pidr = mm->context.id; + dev =to_pci_dev (ctx->afu->fn->dev.parent); rc =ocxl_link_add_pe (ctx->afu->fn->link, ctx->pasid, pidr, ctx->tidr, - amr, mm, xsl_fault_error, ctx); + amr,pci_dev_id (dev), mm, xsl_fault_error, ctx);if (rc) goto out;drivers/misc/ocxl/link.c +3
-1@@ -494,7 +494,7 @@ static u64 calculate_cfg_state(bool kernel) }int ocxl_link_add_pe (void *link_handle,int pasid,u32 pidr,u32 tidr, -u64 amr,struct mm_struct *mm, +u64 amr,u16 bdf,struct mm_struct *mm,void (*xsl_err_cb)(void *data,u64 addr,u64 dsisr),void *xsl_err_data) {@@ -529,6 +529,8 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,memset (pe,0 ,sizeof (struct ocxl_process_element )); pe->config_state =cpu_to_be64 (calculate_cfg_state (pidr ==0 )); + pe->pasid =cpu_to_be32 (pasid << (31 -19 )); + pe->bdf =cpu_to_be16 (bdf); pe->lpid =cpu_to_be32 (mfspr (SPRN_LPID )); pe->pid =cpu_to_be32 (pidr); pe->tid =cpu_to_be32 (tidr);drivers/misc/ocxl/ocxl_internal.h +6
-3@@ -84,13 +84,16 @@ struct ocxl_context {struct ocxl_process_element {__be64 config_state; -__be32 reserved1[11 ]; +__be32 pasid; +__be16 bdf; +__be16 reserved1; +__be32 reserved2[9 ];__be32 lpid;__be32 tid;__be32 pid; -__be32 reserved2[10 ]; +__be32 reserved3[10 ];__be64 amr; -__be32 reserved3[3 ]; +__be32 reserved4[3 ];__be32 software_state; };drivers/scsi/cxlflash/ocxl_hw.c +4
-2@@ -329,6 +329,7 @@ static int start_context(struct ocxlflash_context *ctx)struct ocxl_hw_afu *afu = ctx->hw_afu;struct ocxl_afu_config *acfg = &afu->acfg;void *link_token = afu->link_token; +struct pci_dev *pdev = afu->pdev;struct device *dev = afu->dev;bool master = ctx->master;struct mm_struct *mm;@@ -360,8 +361,9 @@ static int start_context(struct ocxlflash_context *ctx) mm = current->mm; } - rc =ocxl_link_add_pe (link_token, ctx->pe, pid,0 ,0 , mm, - ocxlflash_xsl_fault, ctx); + rc =ocxl_link_add_pe (link_token, ctx->pe, pid,0 ,0 , +pci_dev_id (pdev), mm, ocxlflash_xsl_fault, + ctx);if (unlikely (rc)) {dev_err (dev,"%s: ocxl_link_add_pe failed rc=%d\n" , __func__, rc);include/misc/ocxl.h +1
-1@@ -447,7 +447,7 @@ void ocxl_link_release(struct pci_dev *dev, void *link_handle);* defined */ int ocxl_link_add_pe (void *link_handle,int pasid,u32 pidr,u32 tidr, -u64 amr,struct mm_struct *mm, +u64 amr,u16 bdf,struct mm_struct *mm,void (*xsl_err_cb)(void *data,u64 addr,u64 dsisr),void *xsl_err_data);
PATCH v3 4/5 ocxl: Add mmu notifier
In reply to Christophe LombardAdd invalidate_range mmu notifier, when required (ATSD access of MMIO registers is available), to initiate TLB invalidation commands. For the time being, the ATSD0 set of registers is used by default.
The pasid and bdf values have to be configured in the Process Element Entry.
The PEE must be set up to match the BDF/PASID of the AFU.
--- drivers/misc/ocxl/link.c | 62 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 61 insertions(+), 1 deletion(-)
drivers/misc/ocxl/link.c +61 -1
@@ -2,8 +2,10 @@// Copyright 2017 IBM Corp. #include <linux/sched/mm.h> #include <linux/mutex.h> +#include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmu_context.h> +#include <linux/mmu_notifier.h> #include <asm/copro.h> #include <asm/pnv-ocxl.h> #include <asm/xive.h>
@@ -33,6 +35,7 @@#define SPA_PE_VALID 0x80000000 +struct ocxl_link ;struct pe_data {struct mm_struct *mm;
@@ -41,6 +44,8 @@ struct pe_data {/* opaque pointer to be passed to the above callback */ void *xsl_err_data;struct rcu_head rcu; +struct ocxl_link *link; +struct mmu_notifier mmu_notifier; };struct spa {
@@ -83,6 +88,8 @@ struct ocxl_link {int domain;int bus;int dev; +void __iomem *arva;/* ATSD register virtual address */ +spinlock_t atsd_lock;/* to serialize shootdowns */ atomic_t irq_available;struct spa *spa;void *platform_data;
@@ -388,6 +395,7 @@ static int alloc_link(struct pci_dev *dev, int PE_mask, struct ocxl_link **out_l link->bus = dev->bus->number; link->dev =PCI_SLOT (dev->devfn);atomic_set (&link->irq_available,MAX_IRQ_PER_LINK ); +spin_lock_init (&link->atsd_lock); rc =alloc_spa (dev, link);if (rc)
@@ -403,6 +411,13 @@ static int alloc_link(struct pci_dev *dev, int PE_mask, struct ocxl_link **out_lif (rc) goto err_xsl_irq; +/* if link->arva is not defeined, MMIO registers are not used to +* generate TLB invalidate. PowerBus snooping is enabled. +* Otherwise, PowerBus snooping is disabled. TLB Invalidates are +* initiated using MMIO registers. +*/ +pnv_ocxl_map_lpar (dev,mfspr (SPRN_LPID ),0 , &link->arva); + *out_link = link;return 0 ;
@@ -454,6 +469,11 @@ static void release_xsl(struct kref *ref) { struct ocxl_link *link = container_of(ref, struct ocxl_link, ref); +if (link->arva) { +pnv_ocxl_unmap_lpar (link->arva); + link->arva =NULL ; + } +list_del (&link->list);/* call platform code before releasing data */ pnv_ocxl_spa_release (link->platform_data);
@@ -470,6 +490,26 @@ void ocxl_link_release(struct pci_dev *dev, void *link_handle) }EXPORT_SYMBOL_GPL (ocxl_link_release); +static void invalidate_range (struct mmu_notifier *mn, +struct mm_struct *mm, +unsigned long start,unsigned long end) +{ + struct pe_data *pe_data = container_of(mn, struct pe_data, mmu_notifier); +struct ocxl_link *link = pe_data->link; +unsigned long addr, pid, page_size =PAGE_SIZE ; + + pid = mm->context.id; + +spin_lock (&link->atsd_lock); +for (addr = start; addr < end; addr += page_size) +pnv_ocxl_tlb_invalidate (link->arva, pid, addr, page_size); +spin_unlock (&link->atsd_lock); +} + +static const struct mmu_notifier_ops ocxl_mmu_notifier_ops = { + .invalidate_range = invalidate_range, +}; +static u64 calculate_cfg_state (bool kernel) {u64 state;
@@ -526,6 +566,8 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr, pe_data->mm = mm; pe_data->xsl_err_cb = xsl_err_cb; pe_data->xsl_err_data = xsl_err_data; + pe_data->link = link; + pe_data->mmu_notifier.ops = &ocxl_mmu_notifier_ops;memset (pe,0 ,sizeof (struct ocxl_process_element )); pe->config_state =cpu_to_be64 (calculate_cfg_state (pidr ==0 ));
@@ -542,8 +584,16 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,* by the nest MMU. If we have a kernel context, TLBIs are * already global. */ -if (mm) +if (mm) {mm_context_add_copro (mm); +if (link->arva) { +/* Use MMIO registers for the TLB Invalidate +* operations. +*/ +mmu_notifier_register (&pe_data->mmu_notifier, mm); + } + } +/* * Barrier is to make sure PE is visible in the SPA before it * is used by the device. It also helps with the global TLBI
@@ -674,6 +724,16 @@ int ocxl_link_remove_pe(void *link_handle, int pasid)WARN (1 ,"Couldn't find pe data when removing PE\n" ); }else {if (pe_data->mm) { +if (link->arva) { +mmu_notifier_unregister (&pe_data->mmu_notifier, + pe_data->mm); +spin_lock (&link->atsd_lock); +pnv_ocxl_tlb_invalidate (link->arva, + pe_data->mm->context.id, +0ull , +PAGE_SIZE ); +spin_unlock (&link->atsd_lock); + }mm_context_remove_copro (pe_data->mm);mmdrop (pe_data->mm); }
Signature · 1 line
2.28.0
Re: [PATCH V3 4/5] ocxl: Add mmu notifier
Quoted 10 lines · Christophe Lombard
Add
invalidate_rangemmu notifier, when required (ATSD access of MMIO registers is available), to initiate TLB invalidation commands. For the time being, the ATSD0 set of registers is used by default.The pasid and bdf values have to be configured in the Process Element Entry.
The PEE must be set up to match the BDF/PASID of the AFU.Signed-off-by Christophe Lombard <[email protected]>---
That looks ok too.
Quoted 150 lines
drivers/misc/ocxl/link.c | 62 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 61 insertions(+), 1 deletion(-)drivers/misc/ocxl/link.c +61
-1@@ -2,8 +2,10 @@// Copyright 2017 IBM Corp. #include <linux/sched/mm.h> #include <linux/mutex.h> +#include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmu_context.h> +#include <linux/mmu_notifier.h> #include <asm/copro.h> #include <asm/pnv-ocxl.h> #include <asm/xive.h> @@ -33,6 +35,7 @@#define SPA_PE_VALID 0x80000000 +struct ocxl_link ;struct pe_data {struct mm_struct *mm;@@ -41,6 +44,8 @@ struct pe_data {/* opaque pointer to be passed to the above callback */ void *xsl_err_data;struct rcu_head rcu; +struct ocxl_link *link; +struct mmu_notifier mmu_notifier; };struct spa {@@ -83,6 +88,8 @@ struct ocxl_link {int domain;int bus;int dev; +void __iomem *arva;/* ATSD register virtual address */ +spinlock_t atsd_lock;/* to serialize shootdowns */ atomic_t irq_available;struct spa *spa;void *platform_data;@@ -388,6 +395,7 @@ static int alloc_link(struct pci_dev *dev, int PE_mask, struct ocxl_link **out_l link->bus = dev->bus->number; link->dev =PCI_SLOT (dev->devfn);atomic_set (&link->irq_available,MAX_IRQ_PER_LINK ); +spin_lock_init (&link->atsd_lock); rc =alloc_spa (dev, link);if (rc)@@ -403,6 +411,13 @@ static int alloc_link(struct pci_dev *dev, int PE_mask, struct ocxl_link **out_lif (rc) goto err_xsl_irq; +/* if link->arva is not defeined, MMIO registers are not used to +* generate TLB invalidate. PowerBus snooping is enabled. +* Otherwise, PowerBus snooping is disabled. TLB Invalidates are +* initiated using MMIO registers. +*/ +pnv_ocxl_map_lpar (dev,mfspr (SPRN_LPID ),0 , &link->arva); + *out_link = link;return 0 ;@@ -454,6 +469,11 @@ static void release_xsl(struct kref *ref) { struct ocxl_link *link = container_of(ref, struct ocxl_link, ref); +if (link->arva) { +pnv_ocxl_unmap_lpar (link->arva); + link->arva =NULL ; + } +list_del (&link->list);/* call platform code before releasing data */ pnv_ocxl_spa_release (link->platform_data);@@ -470,6 +490,26 @@ void ocxl_link_release(struct pci_dev *dev, void *link_handle) }EXPORT_SYMBOL_GPL (ocxl_link_release); +static void invalidate_range (struct mmu_notifier *mn, +struct mm_struct *mm, +unsigned long start,unsigned long end) +{ + struct pe_data *pe_data = container_of(mn, struct pe_data, mmu_notifier); +struct ocxl_link *link = pe_data->link; +unsigned long addr, pid, page_size =PAGE_SIZE ; + + pid = mm->context.id; + +spin_lock (&link->atsd_lock); +for (addr = start; addr < end; addr += page_size) +pnv_ocxl_tlb_invalidate (link->arva, pid, addr, page_size); +spin_unlock (&link->atsd_lock); +} + +static const struct mmu_notifier_ops ocxl_mmu_notifier_ops = { + .invalidate_range = invalidate_range, +}; +static u64 calculate_cfg_state (bool kernel) {u64 state;@@ -526,6 +566,8 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr, pe_data->mm = mm; pe_data->xsl_err_cb = xsl_err_cb; pe_data->xsl_err_data = xsl_err_data; + pe_data->link = link; + pe_data->mmu_notifier.ops = &ocxl_mmu_notifier_ops;memset (pe,0 ,sizeof (struct ocxl_process_element )); pe->config_state =cpu_to_be64 (calculate_cfg_state (pidr ==0 ));@@ -542,8 +584,16 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,* by the nest MMU. If we have a kernel context, TLBIs are * already global. */ -if (mm) +if (mm) {mm_context_add_copro (mm); +if (link->arva) { +/* Use MMIO registers for the TLB Invalidate +* operations. +*/ +mmu_notifier_register (&pe_data->mmu_notifier, mm); + } + } +/* * Barrier is to make sure PE is visible in the SPA before it * is used by the device. It also helps with the global TLBI @@ -674,6 +724,16 @@ int ocxl_link_remove_pe(void *link_handle, int pasid)WARN (1 ,"Couldn't find pe data when removing PE\n" ); }else {if (pe_data->mm) { +if (link->arva) { +mmu_notifier_unregister (&pe_data->mmu_notifier, + pe_data->mm); +spin_lock (&link->atsd_lock); +pnv_ocxl_tlb_invalidate (link->arva, + pe_data->mm->context.id, +0ull , +PAGE_SIZE ); +spin_unlock (&link->atsd_lock); + }mm_context_remove_copro (pe_data->mm);mmdrop (pe_data->mm); }
PATCH v3 5/5 ocxl: Add new kernel traces
In reply to Christophe LombardAdd specific kernel traces which provide information on mmu notifier and on pages range.
--- drivers/misc/ocxl/link.c | 4 +++ drivers/misc/ocxl/trace.h | 64 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+)
drivers/misc/ocxl/link.c +4 -0
@@ -499,6 +499,7 @@ static void invalidate_range(struct mmu_notifier *mn,unsigned long addr, pid, page_size =PAGE_SIZE ; pid = mm->context.id; +trace_ocxl_mmu_notifier_range (start, end, pid);spin_lock (&link->atsd_lock);for (addr = start; addr < end; addr += page_size)
@@ -590,6 +591,7 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,/* Use MMIO registers for the TLB Invalidate * operations. */ +trace_ocxl_init_mmu_notifier (pasid, mm->context.id);mmu_notifier_register (&pe_data->mmu_notifier, mm); } }
@@ -725,6 +727,8 @@ int ocxl_link_remove_pe(void *link_handle, int pasid) }else {if (pe_data->mm) {if (link->arva) { +trace_ocxl_release_mmu_notifier (pasid, + pe_data->mm->context.id);mmu_notifier_unregister (&pe_data->mmu_notifier, pe_data->mm);spin_lock (&link->atsd_lock);
drivers/misc/ocxl/trace.h +64 -0
70 lines not on this page · raw message
Signature · 1 line
2.28.0
Re: [PATCH V3 5/5] ocxl: Add new kernel traces
Quoted 5 lines · Christophe Lombard
Add specific kernel traces which provide information on mmu notifier and on pages range.
Signed-off-by Christophe Lombard <[email protected]>---
Quoted 109 lines
drivers/misc/ocxl/link.c | 4 +++ drivers/misc/ocxl/trace.h | 64 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+)drivers/misc/ocxl/link.c +4
-0@@ -499,6 +499,7 @@ static void invalidate_range(struct mmu_notifier *mn,unsigned long addr, pid, page_size =PAGE_SIZE ; pid = mm->context.id; +trace_ocxl_mmu_notifier_range (start, end, pid);spin_lock (&link->atsd_lock);for (addr = start; addr < end; addr += page_size)@@ -590,6 +591,7 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,/* Use MMIO registers for the TLB Invalidate * operations. */ +trace_ocxl_init_mmu_notifier (pasid, mm->context.id);mmu_notifier_register (&pe_data->mmu_notifier, mm); } }@@ -725,6 +727,8 @@ int ocxl_link_remove_pe(void *link_handle, int pasid) }else {if (pe_data->mm) {if (link->arva) { +trace_ocxl_release_mmu_notifier (pasid, + pe_data->mm->context.id);mmu_notifier_unregister (&pe_data->mmu_notifier, pe_data->mm);spin_lock (&link->atsd_lock);drivers/misc/ocxl/trace.h +64
-0@@ -8,6 +8,70 @@#include <linux/tracepoint.h> + +TRACE_EVENT (ocxl_mmu_notifier_range, + TP_PROTO(unsigned long start, unsigned long end, unsigned long pidr), +TP_ARGS (start, end, pidr), + +TP_STRUCT__entry ( + __field(unsigned long, start) + __field(unsigned long, end) + __field(unsigned long, pidr) + ), + +TP_fast_assign ( + __entry->start = start; + __entry->end = end; + __entry->pidr = pidr; + ), + +TP_printk ("start=0x%lx end=0x%lx pidr=0x%lx" , + __entry->start, + __entry->end, + __entry->pidr + ) +); + +TRACE_EVENT (ocxl_init_mmu_notifier, + TP_PROTO(int pasid, unsigned long pidr), +TP_ARGS (pasid, pidr), + +TP_STRUCT__entry ( + __field(int, pasid) + __field(unsigned long, pidr) + ), + +TP_fast_assign ( + __entry->pasid = pasid; + __entry->pidr = pidr; + ), + +TP_printk ("pasid=%d, pidr=0x%lx" , + __entry->pasid, + __entry->pidr + ) +); + +TRACE_EVENT (ocxl_release_mmu_notifier, + TP_PROTO(int pasid, unsigned long pidr), +TP_ARGS (pasid, pidr), + +TP_STRUCT__entry ( + __field(int, pasid) + __field(unsigned long, pidr) + ), + +TP_fast_assign ( + __entry->pasid = pasid; + __entry->pidr = pidr; + ), + +TP_printk ("pasid=%d, pidr=0x%lx" , + __entry->pasid, + __entry->pidr + ) +); + DECLARE_EVENT_CLASS(ocxl_context, TP_PROTO(pid_t pid, void *spa, int pasid, u32 pidr, u32 tidr), TP_ARGS(pid, spa, pasid, pidr, tidr),