From 871e178e0f2c4fa788f694721a10b4758d494ce1 Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Thu, 7 Apr 2016 16:28:26 +1000 Subject: powerpc/pseries/eeh: Handle RTAS delay requests in configure_bridge In the "ibm,configure-pe" and "ibm,configure-bridge" RTAS calls, the spec states that values of 9900-9905 can be returned, indicating that software should delay for 10^x (where x is the last digit, i.e. 990x) milliseconds and attempt the call again. Currently, the kernel doesn't know about this, and respecting it fixes some PCI failures when the hypervisor is busy. The delay is capped at 0.2 seconds. Cc: # 3.10+ Signed-off-by: Russell Currey Acked-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/eeh_pseries.c | 51 ++++++++++++++++++++-------- 1 file changed, 36 insertions(+), 15 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index ac3ffd97e059..405baaf96864 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -615,29 +615,50 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { int config_addr; int ret; + /* Waiting 0.2s maximum before skipping configuration */ + int max_wait = 200; /* Figure out the PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - /* Use new configure-pe function, if supported */ - if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_pe, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else { - return -EFAULT; - } + while (max_wait > 0) { + /* Use new configure-pe function, if supported */ + if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { + ret = rtas_call(ibm_configure_pe, 3, 1, NULL, + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); + } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { + ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); + } else { + return -EFAULT; + } - if (ret) - pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", - __func__, pe->phb->global_number, pe->addr, ret); + if (!ret) + return ret; + + /* + * If RTAS returns a delay value that's above 100ms, cut it + * down to 100ms in case firmware made a mistake. For more + * on how these delay values work see rtas_busy_delay_time + */ + if (ret > RTAS_EXTENDED_DELAY_MIN+2 && + ret <= RTAS_EXTENDED_DELAY_MAX) + ret = RTAS_EXTENDED_DELAY_MIN+2; + + max_wait -= rtas_busy_delay_time(ret); + + if (max_wait < 0) + break; + + rtas_busy_delay(ret); + } + pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, ret); return ret; } -- cgit v1.2.3 From bd000b82e86503d5e8b9e6d40a3257bc9dddb96d Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Thu, 7 Apr 2016 16:28:27 +1000 Subject: powerpc/pseries/eeh: Refactor the configure_bridge RTAS tokens The RTAS calls "ibm,configure-pe" and "ibm,configure-bridge" perform the same actions, however the former can skip configuration if unnecessary. The existing code treats them as different tokens even though only one will ever be called. Refactor this by making a single token that is assigned during init. Signed-off-by: Russell Currey Acked-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/eeh_pseries.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 405baaf96864..3998e0f9a03b 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -53,7 +53,6 @@ static int ibm_read_slot_reset_state2; static int ibm_slot_error_detail; static int ibm_get_config_addr_info; static int ibm_get_config_addr_info2; -static int ibm_configure_bridge; static int ibm_configure_pe; /* @@ -81,7 +80,14 @@ static int pseries_eeh_init(void) ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); ibm_configure_pe = rtas_token("ibm,configure-pe"); - ibm_configure_bridge = rtas_token("ibm,configure-bridge"); + + /* + * ibm,configure-pe and ibm,configure-bridge have the same semantics, + * however ibm,configure-pe can be faster. If we can't find + * ibm,configure-pe then fall back to using ibm,configure-bridge. + */ + if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE) + ibm_configure_pe = rtas_token("ibm,configure-bridge"); /* * Necessary sanity check. We needn't check "get-config-addr-info" @@ -93,8 +99,7 @@ static int pseries_eeh_init(void) (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE && ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) || ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE || - (ibm_configure_pe == RTAS_UNKNOWN_SERVICE && - ibm_configure_bridge == RTAS_UNKNOWN_SERVICE)) { + ibm_configure_pe == RTAS_UNKNOWN_SERVICE) { pr_info("EEH functionality not supported\n"); return -EINVAL; } @@ -624,18 +629,9 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) config_addr = pe->addr; while (max_wait > 0) { - /* Use new configure-pe function, if supported */ - if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_pe, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else { - return -EFAULT; - } + ret = rtas_call(ibm_configure_pe, 3, 1, NULL, + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); if (!ret) return ret; -- cgit v1.2.3 From d23fac2b27d94aeb7b65536a50d32bfdc21fe01e Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Thu, 12 May 2016 13:26:44 +0200 Subject: powerpc: Fix definition of SIAR and SDAR registers The SIAR and SDAR registers are available twice, one time as SPRs 780 / 781 (unprivileged, but read-only), and one time as the SPRs 796 / 797 (privileged, but read and write). The Linux kernel code currently uses the unprivileged SPRs - while this is OK for reading, writing to that register of course does not work. Since the KVM code tries to write to this register, too (see the mtspr in book3s_hv_rmhandlers.S), the contents of this register sometimes get lost for the guests, e.g. during migration of a VM. To fix this issue, simply switch to the privileged SPR numbers instead. Cc: stable@vger.kernel.org Signed-off-by: Thomas Huth Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/reg.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c1e82e968506..c58a3e76caf1 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -754,13 +754,13 @@ #define SPRN_PMC6 792 #define SPRN_PMC7 793 #define SPRN_PMC8 794 -#define SPRN_SIAR 780 -#define SPRN_SDAR 781 #define SPRN_SIER 784 #define SIER_SIPR 0x2000000 /* Sampled MSR_PR */ #define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ #define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ #define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ +#define SPRN_SIAR 796 +#define SPRN_SDAR 797 #define SPRN_TACR 888 #define SPRN_TCSCR 889 #define SPRN_CSIGR 890 -- cgit v1.2.3 From 8dd75ccb571f3c92c48014b3dabd3d51a115ab41 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Thu, 12 May 2016 13:29:11 +0200 Subject: powerpc: Use privileged SPR number for MMCR2 We are already using the privileged versions of MMCR0, MMCR1 and MMCRA in the kernel, so for MMCR2, we should better use the privileged versions, too, to be consistent. Fixes: 240686c13687 ("powerpc: Initialise PMU related regs on Power8") Cc: stable@vger.kernel.org # v3.10+ Suggested-by: Paul Mackerras Signed-off-by: Thomas Huth Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c58a3e76caf1..a0948f40bc7b 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -717,7 +717,7 @@ #define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 -#define SPRN_MMCR2 769 +#define SPRN_MMCR2 785 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL -- cgit v1.2.3 From d6c886006c948141f24e84acebfb757d3200f20c Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Tue, 31 May 2016 11:56:29 +0530 Subject: powerpc/mm/radix: Update LPCR only if it is powernv LPCR cannot be updated when running in guest mode. Fixes: 2bfd65e45e87 ("powerpc/mm/radix: Add radix callbacks for early init routines") Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable-radix.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 18b2c11604fa..c939e6e57a9e 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -296,11 +296,6 @@ found: void __init radix__early_init_mmu(void) { unsigned long lpcr; - /* - * setup LPCR UPRT based on mmu_features - */ - lpcr = mfspr(SPRN_LPCR); - mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); #ifdef CONFIG_PPC_64K_PAGES /* PAGE_SIZE mappings */ @@ -343,8 +338,11 @@ void __init radix__early_init_mmu(void) __pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT; radix_init_page_sizes(); - if (!firmware_has_feature(FW_FEATURE_LPAR)) + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); radix_init_partition_table(); + } radix_init_pgtable(); } @@ -353,16 +351,15 @@ void radix__early_init_mmu_secondary(void) { unsigned long lpcr; /* - * setup LPCR UPRT based on mmu_features + * update partition table control register and UPRT */ - lpcr = mfspr(SPRN_LPCR); - mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); - /* - * update partition table control register, 64 K size. - */ - if (!firmware_has_feature(FW_FEATURE_LPAR)) + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); + mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); + } } void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, -- cgit v1.2.3 From dc47c0c1f8099fccb2c1e2f3775855066a9e4484 Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Tue, 31 May 2016 11:56:30 +0530 Subject: powerpc/mm/hash: Fix the reference bit update when handling hash fault When we converted the asm routines to C functions, we missed updating HPTE_R_R based on _PAGE_ACCESSED. ASM code used to copy over the lower bits from pte via. andi. r3,r30,0x1fe /* Get basic set of flags */ We also update the code such that we won't update the Change bit ('C' bit) always. This was added by commit c5cf0e30bf3d8 ("powerpc: Fix buglet with MMU hash management"). With hash64, we need to make sure that hardware doesn't do a pte update directly. This is because we do end up with entries in TLB with no hash page table entry. This happens because when we find a hash bucket full, we "evict" a more/less random entry from it. When we do that we don't invalidate the TLB (hpte_remove) because we assume the old translation is still technically "valid". For more info look at commit 0608d692463("powerpc/mm: Always invalidate tlb on hpte invalidate and update"). Thus it's critical that valid hash PTEs always have reference bit set and writeable ones have change bit set. We do this by hashing a non-dirty linux PTE as read-only and always setting _PAGE_ACCESSED (and thus R) when hashing anything else in. Any attempt by Linux at clearing those bits also removes the corresponding hash entry. Commit 5cf0e30bf3d8 did that for 'C' bit by enabling 'C' bit always. We don't really need to do that because we never map a RW pte entry without setting 'C' bit. On READ fault on a RW pte entry, we still map it READ only, hence a store update in the page will still cause a hash pte fault. This patch reverts the part of commit c5cf0e30bf3d8 ("[PATCH] powerpc: Fix buglet with MMU hash management") and retain the updatepp part. - If we hit the updatepp path on native, the old code without that commit, would fail to set C bcause native_hpte_updatepp() was implemented to filter the same bits as H_PROTECT and not let C through thus we would "upgrade" a RO HPTE to RW without setting C thus causing the bug. So the real fix in that commit was the change to native_hpte_updatepp Fixes: 89ff725051d1 ("powerpc/mm: Convert __hash_page_64K to C") Cc: stable@vger.kernel.org # v4.5+ Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hash_utils_64.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 59268969a0bc..b2740c67e172 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -159,6 +159,19 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = { }, }; +/* + * 'R' and 'C' update notes: + * - Under pHyp or KVM, the updatepp path will not set C, thus it *will* + * create writeable HPTEs without C set, because the hcall H_PROTECT + * that we use in that case will not update C + * - The above is however not a problem, because we also don't do that + * fancy "no flush" variant of eviction and we use H_REMOVE which will + * do the right thing and thus we don't have the race I described earlier + * + * - Under bare metal, we do have the race, so we need R and C set + * - We make sure R is always set and never lost + * - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping + */ unsigned long htab_convert_pte_flags(unsigned long pteflags) { unsigned long rflags = 0; @@ -186,9 +199,14 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) rflags |= 0x1; } /* - * Always add "C" bit for perf. Memory coherence is always enabled + * We can't allow hardware to update hpte bits. Hence always + * set 'R' bit and set 'C' if it is a write fault + * Memory coherence is always enabled */ - rflags |= HPTE_R_C | HPTE_R_M; + rflags |= HPTE_R_R | HPTE_R_M; + + if (pteflags & _PAGE_DIRTY) + rflags |= HPTE_R_C; /* * Add in WIG bits */ -- cgit v1.2.3 From 157d4d0620879b7d89ca1e3cd7bf0be1e29be198 Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Tue, 31 May 2016 11:56:31 +0530 Subject: powerpc/mm/radix: Add missing tlb flush This should not have any impact on hash, because hash does tlb invalidate with every pte update and we don't implement flush_tlb_* functions for hash. With radix we should make an explicit call to flush tlb outside pte update. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable-book3s64.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index eb4451144746..670318766545 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -33,10 +33,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, changed = !pmd_same(*(pmdp), entry); if (changed) { __ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry)); - /* - * Since we are not supporting SW TLB systems, we don't - * have any thing similar to flush_tlb_page_nohash() - */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; } -- cgit v1.2.3 From 7cc851039d643a2ee7df4d18177150f2c3a484f5 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Tue, 31 May 2016 07:51:17 +0200 Subject: powerpc/pseries: Add POWER8NVL support to ibm,client-architecture-support call If we do not provide the PVR for POWER8NVL, a guest on this system currently ends up in PowerISA 2.06 compatibility mode on KVM, since QEMU does not provide a generic PowerISA 2.07 mode yet. So some new instructions from POWER8 (like "mtvsrd") get disabled for the guest, resulting in crashes when using code compiled explicitly for POWER8 (e.g. with the "-mcpu=power8" option of GCC). Fixes: ddee09c099c3 ("powerpc: Add PVR for POWER8NVL processor") Cc: stable@vger.kernel.org # v4.0+ Signed-off-by: Thomas Huth Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/prom_init.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index da5192590c44..ccd2037c797f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -656,6 +656,7 @@ unsigned char ibm_architecture_vec[] = { W(0xffff0000), W(0x003e0000), /* POWER6 */ W(0xffff0000), W(0x003f0000), /* POWER7 */ W(0xffff0000), W(0x004b0000), /* POWER8E */ + W(0xffff0000), W(0x004c0000), /* POWER8NVL */ W(0xffff0000), W(0x004d0000), /* POWER8 */ W(0xffffffff), W(0x0f000004), /* all 2.07-compliant */ W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */ -- cgit v1.2.3